Schedule for time together¶
- Introduction 👋
- Getting Started with Python 🛫
- Setting up your "envrionment" 🎚️
- Analyzing data 📊
- Starting to automate 🤖
Goals for today!¶
We're going to reivew:
- What is Python and its benefits for data analysis...and more importantly automation 🐍
- Installing Python on your machine and the common "packages" that we'll use in data analysis 📦
- Read a data from a csv, webpage, and pdf 👁️🗨️
- Review how to clean columns and data tables 🧹
- Save data into a formatted Excel Workbook 💾
- Write a script for future replication 📜
- Discuss some next steps 🔮
What is Python?¶
"Python is a clear and powerful object-oriented programming language..." (wiki.python.org/moin/BeginnersGuide/Overview)
What is Python?¶
Python is an open-source programming language that has packages built for data analysis.
It was designed for programming first and then the data analysis came second.
It's built on top of C which means that is a bit slower than most programming languages -- but, it is a lot easier to read and write
Why do we use it for data analysis?¶
- Easy-to-use language that makes it easy to "run" 🏃♂️
- Large library of packages for data analysis 📚
- It's open-source (think, "free") 💰
- Easy to learn 💡
- Flexible 🧘♂️
- Fun! 🎉
Why do we use Python?¶
My personal search for a data analysis tool 🚶♂️
Code allows for documentation and reproducibility 📄
We can utilize other resources of the computer 💻
Installing Python¶
Apple Computers
https://www.groovypost.com/howto/install-pip-on-a-mac/
Windows Computers
https://www.activestate.com/resources/quick-reads/how-to-install-pip-on-windows/
Installing Pacakges¶
Windows Key + r
Type 'cmd' + enter
- pip install numpy
- pip install pandas
- pip install jupyterlab
- pip install statsmodels.formula.api
- pip install matplotlib
- pip install seaborn
- pip install -q tabula-py
Downloading the files¶
https://github.com/mgreen216/automateir
Save your files to one folder location example: "C:\users\\[user_name]\Documents\Automate"
Jupyter Notebook and Lab¶
- Allows to run code in a "cell"
- Good for data analysis and testing
Starting Jupyter Lab¶
Windows Key + r
Type 'cmd' + enter
Type 'jupyter-lab' + enter
In [2]:
print('Hello, world!')
Hello, world!
In [3]:
# Build your first function!
def square_list(x):
return(x**2)
for i in range(6):
print(i, square_list(i))
0 0 1 1 2 4 3 9 4 16 5 25
In [4]:
# Build your first function!
def square_list(x):
return(x**2)
for i in range(6):
print(i, square_list(i))
0 0 1 1 2 4 3 9 4 16 5 25
Python Data Structures¶
- Lists
In [5]:
newList = ['Philadelphia', 'Green', 'Seven']
print(newList)
['Philadelphia', 'Green', 'Seven']
In [6]:
newList.append('PA')
print(newList)
['Philadelphia', 'Green', 'Seven', 'PA']
Dictionaries¶
- Ordered pairs
- Called Keys and Values
- Can store text and string
In [7]:
myDict = {1: 'One', 2: 'Two', 3: 3}
In [8]:
myDict[2]
Out[8]:
'Two'
In [9]:
myDict.values()
Out[9]:
dict_values(['One', 'Two', 3])
In [10]:
myDict.keys()
Out[10]:
dict_keys([1, 2, 3])
In [11]:
import numpy as np
In [12]:
newArray = np.array(newList)
print(newArray)
['Philadelphia' 'Green' 'Seven' 'PA']
In [13]:
test_list = [1, 2, 3] + [4, 5, 6]
test_array = np.array([1, 2, 3]) + np.array([4, 5, 6])
print(test_list)
print(test_array)
[1, 2, 3, 4, 5, 6] [5 7 9]
Pandas¶
- A package that allows us to put a series of vectors into a dataframe
- A dataframe is our matrix or, individual spreadsheet from Excel
Dataframes¶
- Used for statisitcal analysis
A widely used Python package. It provides data structures suitable for statisical analysis, and adds functions that facilitate data input, data organization, data manipulation.
In [14]:
import pandas as pd
import numpy as np
import seaborn as sns
%matplotlib inline
# We'll create a dataframe from 3 different arrays
c = np.arange(1,11,0.1) # This creates an array starting at 1 ending before 11, that increases by 0.1
x = np.reciprocal(c).round(1) # This is the reciprocal of the c array we just created
y = np.log10(c).round(1) # Log of our array c
df = pd.DataFrame({'Counter': c, 'x':x, 'y':y})
In [15]:
# Let's check the top 5 values of the dataframe
df.head()
Out[15]:
| Counter | x | y | |
|---|---|---|---|
| 0 | 1.0 | 1.0 | 0.0 |
| 1 | 1.1 | 0.9 | 0.0 |
| 2 | 1.2 | 0.8 | 0.1 |
| 3 | 1.3 | 0.8 | 0.1 |
| 4 | 1.4 | 0.7 | 0.1 |
In [16]:
# There are two ways to value the values of a signle column
df['Counter']
Out[16]:
0 1.0
1 1.1
2 1.2
3 1.3
4 1.4
...
95 10.5
96 10.6
97 10.7
98 10.8
99 10.9
Name: Counter, Length: 100, dtype: float64
In [17]:
df.Counter
Out[17]:
0 1.0
1 1.1
2 1.2
3 1.3
4 1.4
...
95 10.5
96 10.6
97 10.7
98 10.8
99 10.9
Name: Counter, Length: 100, dtype: float64
In [18]:
# We can also slice a column by calling the colunm names in a list
data = df[['Counter', 'y']]
data.head()
Out[18]:
| Counter | y | |
|---|---|---|
| 0 | 1.0 | 0.0 |
| 1 | 1.1 | 0.0 |
| 2 | 1.2 | 0.1 |
| 3 | 1.3 | 0.1 |
| 4 | 1.4 | 0.1 |
In [19]:
# We can also slice and anaylze sections of a dataframe through referencing the index
df[4:10]
Out[19]:
| Counter | x | y | |
|---|---|---|---|
| 4 | 1.4 | 0.7 | 0.1 |
| 5 | 1.5 | 0.7 | 0.2 |
| 6 | 1.6 | 0.6 | 0.2 |
| 7 | 1.7 | 0.6 | 0.2 |
| 8 | 1.8 | 0.6 | 0.3 |
| 9 | 1.9 | 0.5 | 0.3 |
In [20]:
df[['Counter', 'y']][4:10]
Out[20]:
| Counter | y | |
|---|---|---|
| 4 | 1.4 | 0.1 |
| 5 | 1.5 | 0.2 |
| 6 | 1.6 | 0.2 |
| 7 | 1.7 | 0.2 |
| 8 | 1.8 | 0.3 |
| 9 | 1.9 | 0.3 |
In [21]:
df.iloc[4:10, [0,2]]
Out[21]:
| Counter | y | |
|---|---|---|
| 4 | 1.4 | 0.1 |
| 5 | 1.5 | 0.2 |
| 6 | 1.6 | 0.2 |
| 7 | 1.7 | 0.2 |
| 8 | 1.8 | 0.3 |
| 9 | 1.9 | 0.3 |
In [22]:
# We can get an array of arrays by calling the values function
df.values
Out[22]:
array([[ 1. , 1. , 0. ],
[ 1.1, 0.9, 0. ],
[ 1.2, 0.8, 0.1],
[ 1.3, 0.8, 0.1],
[ 1.4, 0.7, 0.1],
[ 1.5, 0.7, 0.2],
[ 1.6, 0.6, 0.2],
[ 1.7, 0.6, 0.2],
[ 1.8, 0.6, 0.3],
[ 1.9, 0.5, 0.3],
[ 2. , 0.5, 0.3],
[ 2.1, 0.5, 0.3],
[ 2.2, 0.5, 0.3],
[ 2.3, 0.4, 0.4],
[ 2.4, 0.4, 0.4],
[ 2.5, 0.4, 0.4],
[ 2.6, 0.4, 0.4],
[ 2.7, 0.4, 0.4],
[ 2.8, 0.4, 0.4],
[ 2.9, 0.3, 0.5],
[ 3. , 0.3, 0.5],
[ 3.1, 0.3, 0.5],
[ 3.2, 0.3, 0.5],
[ 3.3, 0.3, 0.5],
[ 3.4, 0.3, 0.5],
[ 3.5, 0.3, 0.5],
[ 3.6, 0.3, 0.6],
[ 3.7, 0.3, 0.6],
[ 3.8, 0.3, 0.6],
[ 3.9, 0.3, 0.6],
[ 4. , 0.2, 0.6],
[ 4.1, 0.2, 0.6],
[ 4.2, 0.2, 0.6],
[ 4.3, 0.2, 0.6],
[ 4.4, 0.2, 0.6],
[ 4.5, 0.2, 0.7],
[ 4.6, 0.2, 0.7],
[ 4.7, 0.2, 0.7],
[ 4.8, 0.2, 0.7],
[ 4.9, 0.2, 0.7],
[ 5. , 0.2, 0.7],
[ 5.1, 0.2, 0.7],
[ 5.2, 0.2, 0.7],
[ 5.3, 0.2, 0.7],
[ 5.4, 0.2, 0.7],
[ 5.5, 0.2, 0.7],
[ 5.6, 0.2, 0.7],
[ 5.7, 0.2, 0.8],
[ 5.8, 0.2, 0.8],
[ 5.9, 0.2, 0.8],
[ 6. , 0.2, 0.8],
[ 6.1, 0.2, 0.8],
[ 6.2, 0.2, 0.8],
[ 6.3, 0.2, 0.8],
[ 6.4, 0.2, 0.8],
[ 6.5, 0.2, 0.8],
[ 6.6, 0.2, 0.8],
[ 6.7, 0.1, 0.8],
[ 6.8, 0.1, 0.8],
[ 6.9, 0.1, 0.8],
[ 7. , 0.1, 0.8],
[ 7.1, 0.1, 0.9],
[ 7.2, 0.1, 0.9],
[ 7.3, 0.1, 0.9],
[ 7.4, 0.1, 0.9],
[ 7.5, 0.1, 0.9],
[ 7.6, 0.1, 0.9],
[ 7.7, 0.1, 0.9],
[ 7.8, 0.1, 0.9],
[ 7.9, 0.1, 0.9],
[ 8. , 0.1, 0.9],
[ 8.1, 0.1, 0.9],
[ 8.2, 0.1, 0.9],
[ 8.3, 0.1, 0.9],
[ 8.4, 0.1, 0.9],
[ 8.5, 0.1, 0.9],
[ 8.6, 0.1, 0.9],
[ 8.7, 0.1, 0.9],
[ 8.8, 0.1, 0.9],
[ 8.9, 0.1, 0.9],
[ 9. , 0.1, 1. ],
[ 9.1, 0.1, 1. ],
[ 9.2, 0.1, 1. ],
[ 9.3, 0.1, 1. ],
[ 9.4, 0.1, 1. ],
[ 9.5, 0.1, 1. ],
[ 9.6, 0.1, 1. ],
[ 9.7, 0.1, 1. ],
[ 9.8, 0.1, 1. ],
[ 9.9, 0.1, 1. ],
[10. , 0.1, 1. ],
[10.1, 0.1, 1. ],
[10.2, 0.1, 1. ],
[10.3, 0.1, 1. ],
[10.4, 0.1, 1. ],
[10.5, 0.1, 1. ],
[10.6, 0.1, 1. ],
[10.7, 0.1, 1. ],
[10.8, 0.1, 1. ],
[10.9, 0.1, 1. ]])
In [23]:
# Or a single array by calling it on a single column
df.y.values
Out[23]:
array([0. , 0. , 0.1, 0.1, 0.1, 0.2, 0.2, 0.2, 0.3, 0.3, 0.3, 0.3, 0.3,
0.4, 0.4, 0.4, 0.4, 0.4, 0.4, 0.5, 0.5, 0.5, 0.5, 0.5, 0.5, 0.5,
0.6, 0.6, 0.6, 0.6, 0.6, 0.6, 0.6, 0.6, 0.6, 0.7, 0.7, 0.7, 0.7,
0.7, 0.7, 0.7, 0.7, 0.7, 0.7, 0.7, 0.7, 0.8, 0.8, 0.8, 0.8, 0.8,
0.8, 0.8, 0.8, 0.8, 0.8, 0.8, 0.8, 0.8, 0.8, 0.9, 0.9, 0.9, 0.9,
0.9, 0.9, 0.9, 0.9, 0.9, 0.9, 0.9, 0.9, 0.9, 0.9, 0.9, 0.9, 0.9,
0.9, 0.9, 1. , 1. , 1. , 1. , 1. , 1. , 1. , 1. , 1. , 1. , 1. ,
1. , 1. , 1. , 1. , 1. , 1. , 1. , 1. , 1. ])
Grouping¶
- Pandas offers functions to handle data, including missing data. nan's {"Not-A-Number"}
- It allows for pivoting for more efficient data manipulation
- You can group respondents by gender
In [24]:
import pandas as pd
import matplotlib.pyplot as plt
import seaborn as sns
In [25]:
data = pd.DataFrame({
'Sex': ['F', 'F', 'M', 'F', 'M',
'M', 'F','M', 'F', 'M', 'M'],
'GPA' : [3.41, 3.53, 2.67, 3.19, 4., 2.15, 3.26, 3.91, 3.75, 2.14, 3.67]
})
grouped = data.groupby('Sex')
grouped.describe()
Out[25]:
| GPA | ||||||||
|---|---|---|---|---|---|---|---|---|
| count | mean | std | min | 25% | 50% | 75% | max | |
| Sex | ||||||||
| F | 5.0 | 3.428 | 0.223204 | 3.19 | 3.26 | 3.41 | 3.53 | 3.75 |
| M | 6.0 | 3.090 | 0.871711 | 2.14 | 2.28 | 3.17 | 3.85 | 4.00 |
In [26]:
grouped.boxplot()
plt.show()
In [27]:
# Show only the female
df_F = grouped.get_group('F')
df_F
Out[27]:
| Sex | GPA | |
|---|---|---|
| 0 | F | 3.41 |
| 1 | F | 3.53 |
| 3 | F | 3.19 |
| 6 | F | 3.26 |
| 8 | F | 3.75 |
In [28]:
# We then can call descriptive statistics
df_F.std()
Out[28]:
GPA 0.223204 dtype: float64
In [29]:
import numpy as np
import pandas as pd
import statsmodels.formula.api as sm
import seaborn as sns
In [30]:
# Generate a noisy line and save the data in a pandas dataframe
x = np.arange(100)
y = 2.25*x - 6 + np.random.randn(len(x))
df = pd.DataFrame({'x':x, 'y':y})
sns.regplot(x = x, y = y, data = df)
plt.show()
In [31]:
# Generate a noisy line and save the data in a pandas dataframe
x = np.arange(100)
y = 2.25*x - 6 + np.random.randn(len(x))
df = pd.DataFrame({'x':x, 'y':y})
sns.regplot(x = x, y = y, data = df)
plt.show()
IPEDS Data 👩🏽🔬¶
In [32]:
# These are the common ways to import the packages as pd, np, etc... you can import them, however; you'd like.
import pandas as pd
import numpy as np
import matplotlib.pyplot as plt
import seaborn as sns
# We are setting our style for printing graphics.
sns.set_style('whitegrid')
Load the Data 👨🏽💻¶
In [34]:
# We will read a csv file. The ecoding is not always needed. It helps with a downloaded file
df = pd.read_csv('hd2020.csv', encoding = 'latin')
Clean and Explore the Dataset 🧽¶
In [35]:
df.head() # Calls the first 5 rows
Out[35]:
| UNITID | INSTNM | IALIAS | ADDR | CITY | STABBR | ZIP | FIPS | OBEREG | CHFNM | ... | CBSATYPE | CSA | NECTA | COUNTYCD | COUNTYNM | CNGDSTCD | LONGITUD | LATITUDE | DFRCGID | DFRCUSCG | |
|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|
| 0 | 100654 | Alabama A & M University | AAMU | 4900 Meridian Street | Normal | AL | 35762 | 1 | 5 | Dr. Andrew Hugine, Jr. | ... | 1 | 290 | -2 | 1089 | Madison County | 105 | -86.568502 | 34.783368 | 109 | 1 |
| 1 | 100663 | University of Alabama at Birmingham | Administration Bldg Suite 1070 | Birmingham | AL | 35294-0110 | 1 | 5 | Ray L. Watts | ... | 1 | 142 | -2 | 1073 | Jefferson County | 107 | -86.799345 | 33.505697 | 95 | 1 | |
| 2 | 100690 | Amridge University | Southern Christian University Regions University | 1200 Taylor Rd | Montgomery | AL | 36117-3553 | 1 | 5 | Michael C.Turner | ... | 1 | 388 | -2 | 1101 | Montgomery County | 102 | -86.174010 | 32.362609 | 126 | 2 |
| 3 | 100706 | University of Alabama in Huntsville | UAH University of Alabama Huntsville | 301 Sparkman Dr | Huntsville | AL | 35899 | 1 | 5 | Darren Dawson | ... | 1 | 290 | -2 | 1089 | Madison County | 105 | -86.640449 | 34.724557 | 99 | 2 |
| 4 | 100724 | Alabama State University | 915 S Jackson Street | Montgomery | AL | 36104-0271 | 1 | 5 | Quinton T. Ross | ... | 1 | 388 | -2 | 1101 | Montgomery County | 107 | -86.295677 | 32.364317 | 118 | 1 |
5 rows × 73 columns
In [36]:
df.tail() # Returns the last 5 rows
Out[36]:
| UNITID | INSTNM | IALIAS | ADDR | CITY | STABBR | ZIP | FIPS | OBEREG | CHFNM | ... | CBSATYPE | CSA | NECTA | COUNTYCD | COUNTYNM | CNGDSTCD | LONGITUD | LATITUDE | DFRCGID | DFRCUSCG | |
|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|
| 6435 | 496335 | Coastline Beauty College - Hemet | 2627 West Florida Avenue Suite 100 | Hemet | CA | 92545-3661 | 6 | 8 | ... | 1 | 348 | -2 | 6065 | Riverside County | 636 | -116.999900 | 33.746000 | -2 | -2 | ||
| 6436 | 496371 | Elite Welding Academy | South Point | 1910 County Road One | South Point | OH | 45680-8849 | 39 | 3 | Bob Reeves | ... | 1 | 170 | -2 | 39087 | Lawrence County | 3906 | -82.594354 | 38.447233 | 217 | 2 |
| 6437 | 496380 | Medspa Academies - NIMA National Institute of ... | 3993 Howard Hughes Parkway Suite 150 | Las Vegas | NV | 89169-6745 | 32 | 8 | ... | 1 | 332 | -2 | 32003 | Clark County | 3201 | -115.158153 | 36.117261 | -2 | -2 | ||
| 6438 | 496414 | TechSherpas 365 | 10213 Wilsky Blvd | Tampa | FL | 33625 | 12 | 5 | Della Wyler | ... | 1 | -2 | -2 | 12057 | Hillsborough County | 1214 | -82.565846 | 28.042450 | -1 | -1 | |
| 6439 | 496423 | Zorganics Institute Beauty and Wellness | ZORGANICS INSTITUTE | 410 WEST BAKERVIEW ROAD SUITE 112 | Bellingham | WA | 98226 | 53 | 8 | Frida Emalange | ... | 1 | -2 | -2 | 53073 | Whatcom County | 5302 | -122.494720 | 48.791194 | 206 | 2 |
5 rows × 73 columns
In [37]:
df.shape
Out[37]:
(6440, 73)
In [38]:
df.info()
<class 'pandas.core.frame.DataFrame'> RangeIndex: 6440 entries, 0 to 6439 Data columns (total 73 columns): # Column Non-Null Count Dtype --- ------ -------------- ----- 0 UNITID 6440 non-null int64 1 INSTNM 6440 non-null object 2 IALIAS 6439 non-null object 3 ADDR 6439 non-null object 4 CITY 6440 non-null object 5 STABBR 6440 non-null object 6 ZIP 6440 non-null object 7 FIPS 6440 non-null int64 8 OBEREG 6440 non-null int64 9 CHFNM 6440 non-null object 10 CHFTITLE 6440 non-null object 11 GENTELE 6440 non-null object 12 EIN 6440 non-null int64 13 DUNS 6440 non-null object 14 OPEID 6440 non-null int64 15 OPEFLAG 6440 non-null int64 16 WEBADDR 6440 non-null object 17 ADMINURL 6440 non-null object 18 FAIDURL 6440 non-null object 19 APPLURL 6440 non-null object 20 NPRICURL 6440 non-null object 21 VETURL 6440 non-null object 22 ATHURL 6440 non-null object 23 DISAURL 6440 non-null object 24 SECTOR 6440 non-null int64 25 ICLEVEL 6440 non-null int64 26 CONTROL 6440 non-null int64 27 HLOFFER 6440 non-null int64 28 UGOFFER 6440 non-null int64 29 GROFFER 6440 non-null int64 30 HDEGOFR1 6440 non-null int64 31 DEGGRANT 6440 non-null int64 32 HBCU 6440 non-null int64 33 HOSPITAL 6440 non-null int64 34 MEDICAL 6440 non-null int64 35 TRIBAL 6440 non-null int64 36 LOCALE 6440 non-null int64 37 OPENPUBL 6440 non-null int64 38 ACT 6440 non-null object 39 NEWID 6440 non-null int64 40 DEATHYR 6440 non-null int64 41 CLOSEDAT 6440 non-null object 42 CYACTIVE 6440 non-null int64 43 POSTSEC 6440 non-null int64 44 PSEFLAG 6440 non-null int64 45 PSET4FLG 6440 non-null int64 46 RPTMTH 6440 non-null int64 47 INSTCAT 6440 non-null int64 48 C18BASIC 6440 non-null int64 49 C18IPUG 6440 non-null int64 50 C18IPGRD 6440 non-null int64 51 C18UGPRF 6440 non-null int64 52 C18ENPRF 6440 non-null int64 53 C18SZSET 6440 non-null int64 54 C15BASIC 6440 non-null int64 55 CCBASIC 6440 non-null int64 56 CARNEGIE 6440 non-null int64 57 LANDGRNT 6440 non-null int64 58 INSTSIZE 6440 non-null int64 59 F1SYSTYP 6440 non-null int64 60 F1SYSNAM 6440 non-null object 61 F1SYSCOD 6440 non-null int64 62 CBSA 6440 non-null int64 63 CBSATYPE 6440 non-null int64 64 CSA 6440 non-null int64 65 NECTA 6440 non-null int64 66 COUNTYCD 6440 non-null int64 67 COUNTYNM 6440 non-null object 68 CNGDSTCD 6440 non-null int64 69 LONGITUD 6440 non-null float64 70 LATITUDE 6440 non-null float64 71 DFRCGID 6440 non-null int64 72 DFRCUSCG 6440 non-null int64 dtypes: float64(2), int64(49), object(22) memory usage: 3.6+ MB
In [39]:
df.columns
Out[39]:
Index(['UNITID', 'INSTNM', 'IALIAS', 'ADDR', 'CITY', 'STABBR', 'ZIP', 'FIPS',
'OBEREG', 'CHFNM', 'CHFTITLE', 'GENTELE', 'EIN', 'DUNS', 'OPEID',
'OPEFLAG', 'WEBADDR', 'ADMINURL', 'FAIDURL', 'APPLURL', 'NPRICURL',
'VETURL', 'ATHURL', 'DISAURL', 'SECTOR', 'ICLEVEL', 'CONTROL',
'HLOFFER', 'UGOFFER', 'GROFFER', 'HDEGOFR1', 'DEGGRANT', 'HBCU',
'HOSPITAL', 'MEDICAL', 'TRIBAL', 'LOCALE', 'OPENPUBL', 'ACT', 'NEWID',
'DEATHYR', 'CLOSEDAT', 'CYACTIVE', 'POSTSEC', 'PSEFLAG', 'PSET4FLG',
'RPTMTH', 'INSTCAT', 'C18BASIC', 'C18IPUG', 'C18IPGRD', 'C18UGPRF',
'C18ENPRF', 'C18SZSET', 'C15BASIC', 'CCBASIC', 'CARNEGIE', 'LANDGRNT',
'INSTSIZE', 'F1SYSTYP', 'F1SYSNAM', 'F1SYSCOD', 'CBSA', 'CBSATYPE',
'CSA', 'NECTA', 'COUNTYCD', 'COUNTYNM', 'CNGDSTCD', 'LONGITUD',
'LATITUDE', 'DFRCGID', 'DFRCUSCG'],
dtype='object')
In [40]:
df.describe(include='all')
Out[40]:
| UNITID | INSTNM | IALIAS | ADDR | CITY | STABBR | ZIP | FIPS | OBEREG | CHFNM | ... | CBSATYPE | CSA | NECTA | COUNTYCD | COUNTYNM | CNGDSTCD | LONGITUD | LATITUDE | DFRCGID | DFRCUSCG | |
|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|
| count | 6440.000000 | 6440 | 6439 | 6439 | 6440 | 6440 | 6440 | 6440.000000 | 6440.000000 | 6440 | ... | 6440.000000 | 6440.000000 | 6440.000000 | 6440.000000 | 6440 | 6440.000000 | 6440.000000 | 6440.000000 | 6440.000000 | 6440.000000 |
| unique | NaN | 6319 | 2074 | 6358 | 2368 | 59 | 5738 | NaN | NaN | 5620 | ... | NaN | NaN | NaN | NaN | 1051 | NaN | NaN | NaN | NaN | NaN |
| top | NaN | Stevens-Henager College | New York | CA | 00961 | NaN | NaN | ... | NaN | NaN | NaN | NaN | Los Angeles County | NaN | NaN | NaN | NaN | NaN | |||
| freq | NaN | 7 | 4253 | 12 | 84 | 700 | 9 | NaN | NaN | 87 | ... | NaN | NaN | NaN | NaN | 203 | NaN | NaN | NaN | NaN | NaN |
| mean | 286466.032764 | NaN | NaN | NaN | NaN | NaN | NaN | 29.175932 | 4.656832 | NaN | ... | 0.970963 | 264.446118 | 3627.057453 | 29229.583385 | NaN | 2926.969720 | -90.507892 | 37.241228 | 101.106211 | 1.455590 |
| std | 139024.241067 | NaN | NaN | NaN | NaN | NaN | NaN | 16.978805 | 2.211014 | NaN | ... | 0.711930 | 181.658369 | 16015.889521 | 16992.453726 | NaN | 1700.057913 | 18.141579 | 5.941976 | 66.491820 | 0.877432 |
| min | 100654.000000 | NaN | NaN | NaN | NaN | NaN | NaN | 1.000000 | 0.000000 | NaN | ... | -2.000000 | -2.000000 | -2.000000 | -2.000000 | NaN | -2.000000 | -170.742774 | -14.322636 | -2.000000 | -2.000000 |
| 25% | 170050.500000 | NaN | NaN | NaN | NaN | NaN | NaN | 13.000000 | 3.000000 | NaN | ... | 1.000000 | 122.000000 | -2.000000 | 13089.000000 | NaN | 1305.000000 | -97.674073 | 33.911633 | 43.000000 | 1.000000 |
| 50% | 221258.500000 | NaN | NaN | NaN | NaN | NaN | NaN | 29.000000 | 5.000000 | NaN | ... | 1.000000 | 297.000000 | -2.000000 | 29189.000000 | NaN | 2907.000000 | -86.392907 | 38.637173 | 99.000000 | 2.000000 |
| 75% | 446568.000000 | NaN | NaN | NaN | NaN | NaN | NaN | 42.000000 | 6.000000 | NaN | ... | 1.000000 | 408.000000 | -2.000000 | 42045.000000 | NaN | 4207.000000 | -78.794307 | 41.250285 | 153.000000 | 2.000000 |
| max | 496423.000000 | NaN | NaN | NaN | NaN | NaN | NaN | 78.000000 | 9.000000 | NaN | ... | 2.000000 | 566.000000 | 79600.000000 | 78030.000000 | NaN | 7898.000000 | 171.378129 | 71.324702 | 231.000000 | 2.000000 |
11 rows × 73 columns
In [41]:
hd = df[['UNITID', 'INSTNM', 'IALIAS', 'CITY', 'STABBR', 'ZIP', 'CHFNM', 'CHFTITLE', 'OPEID', 'SECTOR', 'HBCU', 'HLOFFER', 'UGOFFER']]
In [42]:
hd.head()
Out[42]:
| UNITID | INSTNM | IALIAS | CITY | STABBR | ZIP | CHFNM | CHFTITLE | OPEID | SECTOR | HBCU | HLOFFER | UGOFFER | |
|---|---|---|---|---|---|---|---|---|---|---|---|---|---|
| 0 | 100654 | Alabama A & M University | AAMU | Normal | AL | 35762 | Dr. Andrew Hugine, Jr. | President | 100200 | 1 | 1 | 9 | 1 |
| 1 | 100663 | University of Alabama at Birmingham | Birmingham | AL | 35294-0110 | Ray L. Watts | President | 105200 | 1 | 2 | 9 | 1 | |
| 2 | 100690 | Amridge University | Southern Christian University Regions University | Montgomery | AL | 36117-3553 | Michael C.Turner | President | 2503400 | 2 | 2 | 9 | 1 |
| 3 | 100706 | University of Alabama in Huntsville | UAH University of Alabama Huntsville | Huntsville | AL | 35899 | Darren Dawson | President | 105500 | 1 | 2 | 9 | 1 |
| 4 | 100724 | Alabama State University | Montgomery | AL | 36104-0271 | Quinton T. Ross | President | 100500 | 1 | 1 | 9 | 1 |
In [43]:
for c in hd.iloc[:,1:].columns:
print(str(c) + "\n" + str(hd[c].value_counts()))
INSTNM
Stevens-Henager College 7
Columbia College 5
Brittany Beauty Academy 4
Arthur's Beauty College 4
Eastern Suffolk BOCES 3
..
Cankdeska Cikana Community College 1
Northeastern State University 1
South Texas College 1
Eastern University 1
Virginia University of Lynchburg 1
Name: INSTNM, Length: 6319, dtype: int64
IALIAS
4253
Ogle School 8
Northwest College - School of Beauty 6
SCC 4
Career Quest 4
...
Robert Morris College RMC RMU 1
BGU, Bethany College of Missions, BCOM, Bethany 1
BBC BBC&S Summit U Summit University BBC & S BBS Baptist Bible College of PA Baptist Bible College Baptist Bible Seminary Baptist Bible College & Seminary Baptist Bible College of Pennsylvania Summit University of Pennsylvania SU of Pennsylvania Summit U Summit U of Pennsylvania 1
IMTI 1
The Mount|MWCC 1
Name: IALIAS, Length: 2074, dtype: int64
CITY
New York 84
Chicago 71
Houston 64
Los Angeles 51
Brooklyn 49
..
Macomb 1
Greencastle 1
San Anselmo 1
South Fallsburg 1
Leesport 1
Name: CITY, Length: 2368, dtype: int64
STABBR
CA 700
NY 439
TX 416
FL 356
PA 338
OH 283
IL 256
MI 168
NC 167
NJ 165
PR 155
TN 154
MA 152
MO 150
GA 148
VA 146
AZ 116
LA 115
IN 108
OK 104
WA 103
MN 100
CO 98
SC 96
WI 92
KY 88
AR 86
MD 82
AL 81
IA 80
OR 80
KS 75
WV 73
CT 71
UT 69
MS 56
NM 49
NE 43
ID 40
NV 39
NH 38
ME 37
MT 31
SD 29
ND 27
DC 25
HI 24
RI 22
VT 22
DE 19
AK 10
WY 10
GU 3
FM 1
VI 1
MH 1
MP 1
AS 1
PW 1
Name: STABBR, dtype: int64
ZIP
00961 9
90010 5
60605 5
78229 5
33144 5
..
64850 1
45551 1
93305-1299 1
11218-5611 1
68005-3098 1
Name: ZIP, Length: 5738, dtype: int64
CHFNM
87
Franklin K. Schoeneman 82
George Grayeb 40
Fardad Fateri 25
Mitch Charles 18
..
Kathleen Rose 1
Rick Brewer 1
Elizabeth Fogle 1
Dr. Ellen Gambino 1
Timothy Hood 1
Name: CHFNM, Length: 5620, dtype: int64
CHFTITLE
President 3240
Chancellor 258
Director 230
CEO 189
Owner 172
...
Chief Adminstrator Officer 1
Owner/CFO 1
Director of CTE 1
Academy Director 1
Operation & Financial Aid Leader 1
Name: CHFTITLE, Length: 595, dtype: int64
OPEID
-2 31
202500 3
332900 3
245300 2
1303900 2
..
4176000 1
2526100 1
175000 1
293600 1
4016500 1
Name: OPEID, Length: 6369, dtype: int64
SECTOR
2 1673
9 1504
4 930
1 806
6 588
3 367
7 235
5 147
0 72
8 66
99 52
Name: SECTOR, dtype: int64
HBCU
2 6338
1 102
Name: HBCU, dtype: int64
HLOFFER
2 1629
9 1256
3 1110
5 740
7 737
4 575
1 176
8 151
-3 52
6 14
Name: HLOFFER, dtype: int64
UGOFFER
1 6085
2 303
-3 52
Name: UGOFFER, dtype: int64
In [44]:
figsize = (12, 6)
plt.figure(figsize = figsize)
sns.countplot(x = 'SECTOR', data = hd)
plt.xlabel("Sector of Institution")
plt.ylabel("Number of Institutions")
plt.title("Count of Institutions by Sector")
plt.show()
Reading Tables from a Webpage 😎¶
In [45]:
df = pd.read_html('https://nces.ed.gov/programs/digest/d21/tables/dt21_303.10.asp?current=yes')
In [46]:
print(type(df))
<class 'list'>
In [47]:
print(df)
[ 0 1 \
0 2021 Tables and Figures All Years of Tables and Figures
2
0 Most Recent Full Issue of the Digest , 0 1
0 Previous Page Download Excel (50KB), 0 1
0 Table 303.10. Total fall enrollment in degree-granting posts..., Year Totalenrollment Attendance status \
Year Totalenrollment Full-time Part-time Percentpart-time
Year Totalenrollment Full-time Part-time Percentpart-time
1 2 3 4 4.1 5
0 19471 2338226 --- --- NaN ---
1 19481 2403396 --- --- NaN ---
2 19491 2444900 --- --- NaN ---
3 19501 2281298 --- --- NaN ---
4 19511 2101962 --- --- NaN ---
.. ... ... ... ... .. ...
76 20265 20054000 12182000 7872000 NaN 39.3
77 20275 20169000 12241000 7928000 NaN 39.3
78 20285 20282000 12301000 7980000 NaN 39.3
79 20295 20393000 12361000 8032000 NaN 39.4
80 20305 20482000 12402000 8080000 NaN 39.4
Sex of student Control of institution \
Male Female Percentfemale Public Private
Male Female Percentfemale Public Total
6 7 8 9 10
0 1659249 678977 29.0 1152377 1185849
1 1709367 694029 28.9 1185588 1217808
2 1721572 723328 29.6 1207151 1237749
3 1560392 720906 31.6 1139699 1141599
4 1390740 711222 33.8 1037938 1064024
.. ... ... ... ... ...
76 8497000 11557000 57.6 14801000 5253000
77 8550000 11619000 57.6 14882000 5287000
78 8603000 11679000 57.6 14960000 5322000
79 8656000 11737000 57.6 15038000 5355000
80 8700000 11783000 57.5 15101000 5381000
Nonprofit For-profit
11 12 12.1
0 --- --- NaN
1 --- --- NaN
2 --- --- NaN
3 --- --- NaN
4 --- --- NaN
.. ... ... ...
76 --- --- NaN
77 --- --- NaN
78 --- --- NaN
79 --- --- NaN
80 --- --- NaN
[81 rows x 14 columns], 0 \
0 ---Not available.
1 1 Degree-credit enrollment only.
2 2 Includes part-time resident students and all...
3 3 Large increases are due to the addition of s...
4 4 Because of imputation techniques, data are n...
5 5 Projected.
6 NOTE: Data in this table represent the 50 stat...
7 SOURCE: U.S. Department of Education, National...
1 \
0 ---Not available.
1 1 Degree-credit enrollment only.
2 2 Includes part-time resident students and all...
3 3 Large increases are due to the addition of s...
4 4 Because of imputation techniques, data are n...
5 5 Projected.
6 NOTE: Data in this table represent the 50 stat...
7 SOURCE: U.S. Department of Education, National...
2 \
0 ---Not available.
1 1 Degree-credit enrollment only.
2 2 Includes part-time resident students and all...
3 3 Large increases are due to the addition of s...
4 4 Because of imputation techniques, data are n...
5 5 Projected.
6 NOTE: Data in this table represent the 50 stat...
7 SOURCE: U.S. Department of Education, National...
3 \
0 ---Not available.
1 1 Degree-credit enrollment only.
2 2 Includes part-time resident students and all...
3 3 Large increases are due to the addition of s...
4 4 Because of imputation techniques, data are n...
5 5 Projected.
6 NOTE: Data in this table represent the 50 stat...
7 SOURCE: U.S. Department of Education, National...
4 \
0 ---Not available.
1 1 Degree-credit enrollment only.
2 2 Includes part-time resident students and all...
3 3 Large increases are due to the addition of s...
4 4 Because of imputation techniques, data are n...
5 5 Projected.
6 NOTE: Data in this table represent the 50 stat...
7 SOURCE: U.S. Department of Education, National...
5 \
0 ---Not available.
1 1 Degree-credit enrollment only.
2 2 Includes part-time resident students and all...
3 3 Large increases are due to the addition of s...
4 4 Because of imputation techniques, data are n...
5 5 Projected.
6 NOTE: Data in this table represent the 50 stat...
7 SOURCE: U.S. Department of Education, National...
6 \
0 ---Not available.
1 1 Degree-credit enrollment only.
2 2 Includes part-time resident students and all...
3 3 Large increases are due to the addition of s...
4 4 Because of imputation techniques, data are n...
5 5 Projected.
6 NOTE: Data in this table represent the 50 stat...
7 SOURCE: U.S. Department of Education, National...
7 \
0 ---Not available.
1 1 Degree-credit enrollment only.
2 2 Includes part-time resident students and all...
3 3 Large increases are due to the addition of s...
4 4 Because of imputation techniques, data are n...
5 5 Projected.
6 NOTE: Data in this table represent the 50 stat...
7 SOURCE: U.S. Department of Education, National...
8 \
0 ---Not available.
1 1 Degree-credit enrollment only.
2 2 Includes part-time resident students and all...
3 3 Large increases are due to the addition of s...
4 4 Because of imputation techniques, data are n...
5 5 Projected.
6 NOTE: Data in this table represent the 50 stat...
7 SOURCE: U.S. Department of Education, National...
9 \
0 ---Not available.
1 1 Degree-credit enrollment only.
2 2 Includes part-time resident students and all...
3 3 Large increases are due to the addition of s...
4 4 Because of imputation techniques, data are n...
5 5 Projected.
6 NOTE: Data in this table represent the 50 stat...
7 SOURCE: U.S. Department of Education, National...
10 \
0 ---Not available.
1 1 Degree-credit enrollment only.
2 2 Includes part-time resident students and all...
3 3 Large increases are due to the addition of s...
4 4 Because of imputation techniques, data are n...
5 5 Projected.
6 NOTE: Data in this table represent the 50 stat...
7 SOURCE: U.S. Department of Education, National...
11 \
0 ---Not available.
1 1 Degree-credit enrollment only.
2 2 Includes part-time resident students and all...
3 3 Large increases are due to the addition of s...
4 4 Because of imputation techniques, data are n...
5 5 Projected.
6 NOTE: Data in this table represent the 50 stat...
7 SOURCE: U.S. Department of Education, National...
12 \
0 ---Not available.
1 1 Degree-credit enrollment only.
2 2 Includes part-time resident students and all...
3 3 Large increases are due to the addition of s...
4 4 Because of imputation techniques, data are n...
5 5 Projected.
6 NOTE: Data in this table represent the 50 stat...
7 SOURCE: U.S. Department of Education, National...
13
0 ---Not available.
1 1 Degree-credit enrollment only.
2 2 Includes part-time resident students and all...
3 3 Large increases are due to the addition of s...
4 4 Because of imputation techniques, data are n...
5 5 Projected.
6 NOTE: Data in this table represent the 50 stat...
7 SOURCE: U.S. Department of Education, National... , 0 1 \
0 2021 Tables and Figures All Years of Tables and Figures
2
0 Most Recent Full Issue of the Digest , 0 1
0 Previous Page Download Excel (50KB)]
In [48]:
df[2]
Out[48]:
| 0 | 1 | |
|---|---|---|
| 0 | Table 303.10. | Total fall enrollment in degree-granting posts... |
In [49]:
df[3]
Out[49]:
| Year | Totalenrollment | Attendance status | Sex of student | Control of institution | ||||||||||
|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|
| Year | Totalenrollment | Full-time | Part-time | Percentpart-time | Male | Female | Percentfemale | Public | Private | |||||
| Year | Totalenrollment | Full-time | Part-time | Percentpart-time | Male | Female | Percentfemale | Public | Total | Nonprofit | For-profit | |||
| 1 | 2 | 3 | 4 | 4.1 | 5 | 6 | 7 | 8 | 9 | 10 | 11 | 12 | 12.1 | |
| 0 | 19471 | 2338226 | --- | --- | NaN | --- | 1659249 | 678977 | 29.0 | 1152377 | 1185849 | --- | --- | NaN |
| 1 | 19481 | 2403396 | --- | --- | NaN | --- | 1709367 | 694029 | 28.9 | 1185588 | 1217808 | --- | --- | NaN |
| 2 | 19491 | 2444900 | --- | --- | NaN | --- | 1721572 | 723328 | 29.6 | 1207151 | 1237749 | --- | --- | NaN |
| 3 | 19501 | 2281298 | --- | --- | NaN | --- | 1560392 | 720906 | 31.6 | 1139699 | 1141599 | --- | --- | NaN |
| 4 | 19511 | 2101962 | --- | --- | NaN | --- | 1390740 | 711222 | 33.8 | 1037938 | 1064024 | --- | --- | NaN |
| ... | ... | ... | ... | ... | ... | ... | ... | ... | ... | ... | ... | ... | ... | ... |
| 76 | 20265 | 20054000 | 12182000 | 7872000 | NaN | 39.3 | 8497000 | 11557000 | 57.6 | 14801000 | 5253000 | --- | --- | NaN |
| 77 | 20275 | 20169000 | 12241000 | 7928000 | NaN | 39.3 | 8550000 | 11619000 | 57.6 | 14882000 | 5287000 | --- | --- | NaN |
| 78 | 20285 | 20282000 | 12301000 | 7980000 | NaN | 39.3 | 8603000 | 11679000 | 57.6 | 14960000 | 5322000 | --- | --- | NaN |
| 79 | 20295 | 20393000 | 12361000 | 8032000 | NaN | 39.4 | 8656000 | 11737000 | 57.6 | 15038000 | 5355000 | --- | --- | NaN |
| 80 | 20305 | 20482000 | 12402000 | 8080000 | NaN | 39.4 | 8700000 | 11783000 | 57.5 | 15101000 | 5381000 | --- | --- | NaN |
81 rows × 14 columns
In [50]:
enroll_df = df[3]
In [51]:
enroll_df.head()
# Found the data table -- what is up with the columns?
Out[51]:
| Year | Totalenrollment | Attendance status | Sex of student | Control of institution | ||||||||||
|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|
| Year | Totalenrollment | Full-time | Part-time | Percentpart-time | Male | Female | Percentfemale | Public | Private | |||||
| Year | Totalenrollment | Full-time | Part-time | Percentpart-time | Male | Female | Percentfemale | Public | Total | Nonprofit | For-profit | |||
| 1 | 2 | 3 | 4 | 4.1 | 5 | 6 | 7 | 8 | 9 | 10 | 11 | 12 | 12.1 | |
| 0 | 19471 | 2338226 | --- | --- | NaN | --- | 1659249 | 678977 | 29.0 | 1152377 | 1185849 | --- | --- | NaN |
| 1 | 19481 | 2403396 | --- | --- | NaN | --- | 1709367 | 694029 | 28.9 | 1185588 | 1217808 | --- | --- | NaN |
| 2 | 19491 | 2444900 | --- | --- | NaN | --- | 1721572 | 723328 | 29.6 | 1207151 | 1237749 | --- | --- | NaN |
| 3 | 19501 | 2281298 | --- | --- | NaN | --- | 1560392 | 720906 | 31.6 | 1139699 | 1141599 | --- | --- | NaN |
| 4 | 19511 | 2101962 | --- | --- | NaN | --- | 1390740 | 711222 | 33.8 | 1037938 | 1064024 | --- | --- | NaN |
In [52]:
enroll_df.columns
# It's a multiIndex which means its a list of tuples (lists)
Out[52]:
MultiIndex([( 'Year', 'Year', ...),
( 'Totalenrollment', 'Totalenrollment', ...),
( 'Attendance status', 'Full-time', ...),
( 'Attendance status', 'Part-time', ...),
( 'Attendance status', 'Part-time', ...),
( 'Attendance status', 'Percentpart-time', ...),
( 'Sex of student', 'Male', ...),
( 'Sex of student', 'Female', ...),
( 'Sex of student', 'Percentfemale', ...),
('Control of institution', 'Public', ...),
('Control of institution', 'Private', ...),
('Control of institution', 'Private', ...),
('Control of institution', 'Private', ...),
('Control of institution', 'Private', ...)],
)
In [53]:
enroll_df.columns[12][2]
# So we want the 3 value in the tuple or second index!
Out[53]:
'For-profit'
In [54]:
# Let's spend some time here
enroll_df.columns = enroll_df.columns.map(lambda x: x[2])
enroll_df.columns
Out[54]:
Index(['Year', 'Totalenrollment', 'Full-time', 'Part-time', 'Part-time',
'Percentpart-time', 'Male', 'Female', 'Percentfemale', 'Public',
'Total', 'Nonprofit', 'For-profit', 'For-profit'],
dtype='object')
In [55]:
enroll_df.info()
<class 'pandas.core.frame.DataFrame'> RangeIndex: 81 entries, 0 to 80 Data columns (total 14 columns): # Column Non-Null Count Dtype --- ------ -------------- ----- 0 Year 81 non-null int64 1 Totalenrollment 81 non-null int64 2 Full-time 81 non-null object 3 Part-time 81 non-null object 4 Part-time 7 non-null float64 5 Percentpart-time 81 non-null object 6 Male 81 non-null int64 7 Female 81 non-null int64 8 Percentfemale 81 non-null float64 9 Public 81 non-null int64 10 Total 81 non-null int64 11 Nonprofit 81 non-null object 12 For-profit 81 non-null object 13 For-profit 5 non-null float64 dtypes: float64(3), int64(6), object(5) memory usage: 9.0+ KB
In [56]:
enroll_df.head()
# How are we going to clean up the year?
Out[56]:
| Year | Totalenrollment | Full-time | Part-time | Part-time | Percentpart-time | Male | Female | Percentfemale | Public | Total | Nonprofit | For-profit | For-profit | |
|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|
| 0 | 19471 | 2338226 | --- | --- | NaN | --- | 1659249 | 678977 | 29.0 | 1152377 | 1185849 | --- | --- | NaN |
| 1 | 19481 | 2403396 | --- | --- | NaN | --- | 1709367 | 694029 | 28.9 | 1185588 | 1217808 | --- | --- | NaN |
| 2 | 19491 | 2444900 | --- | --- | NaN | --- | 1721572 | 723328 | 29.6 | 1207151 | 1237749 | --- | --- | NaN |
| 3 | 19501 | 2281298 | --- | --- | NaN | --- | 1560392 | 720906 | 31.6 | 1139699 | 1141599 | --- | --- | NaN |
| 4 | 19511 | 2101962 | --- | --- | NaN | --- | 1390740 | 711222 | 33.8 | 1037938 | 1064024 | --- | --- | NaN |
In [57]:
enroll_df['year_clean'] = enroll_df['Year'].astype('str').str[:4]
enroll_df.head()
Out[57]:
| Year | Totalenrollment | Full-time | Part-time | Part-time | Percentpart-time | Male | Female | Percentfemale | Public | Total | Nonprofit | For-profit | For-profit | year_clean | |
|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|
| 0 | 19471 | 2338226 | --- | --- | NaN | --- | 1659249 | 678977 | 29.0 | 1152377 | 1185849 | --- | --- | NaN | 1947 |
| 1 | 19481 | 2403396 | --- | --- | NaN | --- | 1709367 | 694029 | 28.9 | 1185588 | 1217808 | --- | --- | NaN | 1948 |
| 2 | 19491 | 2444900 | --- | --- | NaN | --- | 1721572 | 723328 | 29.6 | 1207151 | 1237749 | --- | --- | NaN | 1949 |
| 3 | 19501 | 2281298 | --- | --- | NaN | --- | 1560392 | 720906 | 31.6 | 1139699 | 1141599 | --- | --- | NaN | 1950 |
| 4 | 19511 | 2101962 | --- | --- | NaN | --- | 1390740 | 711222 | 33.8 | 1037938 | 1064024 | --- | --- | NaN | 1951 |
In [58]:
enroll_df['year_clean'] = enroll_df['Year'].astype('str').str[:4]
enroll_df.head()
Out[58]:
| Year | Totalenrollment | Full-time | Part-time | Part-time | Percentpart-time | Male | Female | Percentfemale | Public | Total | Nonprofit | For-profit | For-profit | year_clean | |
|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|
| 0 | 19471 | 2338226 | --- | --- | NaN | --- | 1659249 | 678977 | 29.0 | 1152377 | 1185849 | --- | --- | NaN | 1947 |
| 1 | 19481 | 2403396 | --- | --- | NaN | --- | 1709367 | 694029 | 28.9 | 1185588 | 1217808 | --- | --- | NaN | 1948 |
| 2 | 19491 | 2444900 | --- | --- | NaN | --- | 1721572 | 723328 | 29.6 | 1207151 | 1237749 | --- | --- | NaN | 1949 |
| 3 | 19501 | 2281298 | --- | --- | NaN | --- | 1560392 | 720906 | 31.6 | 1139699 | 1141599 | --- | --- | NaN | 1950 |
| 4 | 19511 | 2101962 | --- | --- | NaN | --- | 1390740 | 711222 | 33.8 | 1037938 | 1064024 | --- | --- | NaN | 1951 |
In [59]:
years = np.arange(2017, 2028, 1) # Let's create a filter for recent years
recent_years = enroll_df[enroll_df['year_clean'].astype(int).isin(years)]
recent_years
Out[59]:
| Year | Totalenrollment | Full-time | Part-time | Part-time | Percentpart-time | Male | Female | Percentfemale | Public | Total | Nonprofit | For-profit | For-profit | year_clean | |
|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|
| 67 | 2017 | 19778151 | 12076141 | 7702010 | NaN | 38.9 | 8571314 | 11206837 | 56.7 | 14571739 | 5206412 | 4108489 | 1097923 | NaN | 2017 |
| 68 | 2018 | 19651412 | 11989569 | 7661843 | NaN | 39.0 | 8444614 | 11206798 | 57.0 | 14539257 | 5112155 | 4131846 | 980309 | NaN | 2018 |
| 69 | 2019 | 19630178 | 11954413 | 7675765 | NaN | 39.1 | 8363889 | 11266289 | 57.4 | 14503647 | 5126531 | 4135372 | 991159 | NaN | 2019 |
| 70 | 2020 | 18991798 | 11591353 | 7400445 | NaN | 39.0 | 7869545 | 11122253 | 58.6 | 13867239 | 5124559 | 4101019 | 1023540 | NaN | 2020 |
| 71 | 20215 | 20327000 | 12387000 | 7941000 | NaN | 39.1 | 8685000 | 11643000 | 57.3 | 14975000 | 5352000 | --- | --- | NaN | 2021 |
| 72 | 20225 | 20031000 | 12177000 | 7854000 | NaN | 39.2 | 8524000 | 11506000 | 57.4 | 14769000 | 5261000 | --- | --- | NaN | 2022 |
| 73 | 20235 | 19851000 | 12041000 | 7810000 | NaN | 39.3 | 8422000 | 11429000 | 57.6 | 14650000 | 5201000 | --- | --- | NaN | 2023 |
| 74 | 20245 | 19862000 | 12041000 | 7821000 | NaN | 39.4 | 8416000 | 11446000 | 57.6 | 14664000 | 5198000 | --- | --- | NaN | 2024 |
| 75 | 20255 | 19934000 | 12099000 | 7835000 | NaN | 39.3 | 8444000 | 11490000 | 57.6 | 14716000 | 5218000 | --- | --- | NaN | 2025 |
| 76 | 20265 | 20054000 | 12182000 | 7872000 | NaN | 39.3 | 8497000 | 11557000 | 57.6 | 14801000 | 5253000 | --- | --- | NaN | 2026 |
| 77 | 20275 | 20169000 | 12241000 | 7928000 | NaN | 39.3 | 8550000 | 11619000 | 57.6 | 14882000 | 5287000 | --- | --- | NaN | 2027 |
In [60]:
years = np.arange(2017, 2028, 1) # Let's create a filter for recent years
recent_years = enroll_df[enroll_df['year_clean'].astype(int).isin(years)]
recent_years
Out[60]:
| Year | Totalenrollment | Full-time | Part-time | Part-time | Percentpart-time | Male | Female | Percentfemale | Public | Total | Nonprofit | For-profit | For-profit | year_clean | |
|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|
| 67 | 2017 | 19778151 | 12076141 | 7702010 | NaN | 38.9 | 8571314 | 11206837 | 56.7 | 14571739 | 5206412 | 4108489 | 1097923 | NaN | 2017 |
| 68 | 2018 | 19651412 | 11989569 | 7661843 | NaN | 39.0 | 8444614 | 11206798 | 57.0 | 14539257 | 5112155 | 4131846 | 980309 | NaN | 2018 |
| 69 | 2019 | 19630178 | 11954413 | 7675765 | NaN | 39.1 | 8363889 | 11266289 | 57.4 | 14503647 | 5126531 | 4135372 | 991159 | NaN | 2019 |
| 70 | 2020 | 18991798 | 11591353 | 7400445 | NaN | 39.0 | 7869545 | 11122253 | 58.6 | 13867239 | 5124559 | 4101019 | 1023540 | NaN | 2020 |
| 71 | 20215 | 20327000 | 12387000 | 7941000 | NaN | 39.1 | 8685000 | 11643000 | 57.3 | 14975000 | 5352000 | --- | --- | NaN | 2021 |
| 72 | 20225 | 20031000 | 12177000 | 7854000 | NaN | 39.2 | 8524000 | 11506000 | 57.4 | 14769000 | 5261000 | --- | --- | NaN | 2022 |
| 73 | 20235 | 19851000 | 12041000 | 7810000 | NaN | 39.3 | 8422000 | 11429000 | 57.6 | 14650000 | 5201000 | --- | --- | NaN | 2023 |
| 74 | 20245 | 19862000 | 12041000 | 7821000 | NaN | 39.4 | 8416000 | 11446000 | 57.6 | 14664000 | 5198000 | --- | --- | NaN | 2024 |
| 75 | 20255 | 19934000 | 12099000 | 7835000 | NaN | 39.3 | 8444000 | 11490000 | 57.6 | 14716000 | 5218000 | --- | --- | NaN | 2025 |
| 76 | 20265 | 20054000 | 12182000 | 7872000 | NaN | 39.3 | 8497000 | 11557000 | 57.6 | 14801000 | 5253000 | --- | --- | NaN | 2026 |
| 77 | 20275 | 20169000 | 12241000 | 7928000 | NaN | 39.3 | 8550000 | 11619000 | 57.6 | 14882000 | 5287000 | --- | --- | NaN | 2027 |
In [61]:
import matplotlib.pyplot as plt
import seaborn as sns
In [62]:
plt.figure(figsize=(15,6))
sns.set_theme(style="whitegrid", context="talk")
sns.set_color_codes('colorblind')
sns.lineplot(x = 'year_clean', y= 'Totalenrollment', data = recent_years)
plt.xlabel("Year")
plt.ylabel("Total Enrollment")
plt.title("Enrollment and Projected Enrollment for Higher Education")
plt.show()
In [63]:
plt.figure(figsize=(15,6))
sns.set_theme(style="whitegrid", context="talk")
sns.set_color_codes('colorblind')
sns.lineplot(x = 'year_clean', y= 'Totalenrollment', data = recent_years)
plt.xlabel("Year")
plt.ylabel("Total Enrollment")
plt.title("Enrollment and Projected Enrollment for Higher Education")
plt.show()
Reading a PDF¶
In [65]:
from tabula.io import read_pdf
en = read_pdf('EFD2020.pdf', pages='all')
In [66]:
en # We have a list again
Out[66]:
[ UNITID XGRCOHR GRCOHRT XUGENTER UGENTER XPGRCOH PGRCOHR XRRFTCT \
0 100654 R 1525.0 R 1712.0 R 89.0 R
1 100663 R 2102.0 R 3529.0 R 60.0 R
2 100690 A NaN A NaN A NaN R
3 100706 R 1328.0 R 2186.0 R 61.0 R
4 100724 R 926.0 R 1123.0 R 82.0 R
.. ... ... ... ... ... ... ... ...
66 103927 A NaN A NaN A NaN R
67 103945 A NaN A NaN A NaN R
68 103954 A NaN A NaN A NaN R
69 103963 A NaN A NaN A NaN R
70 104090 A NaN A NaN A NaN R
RRFTCT XRRFTEX ... XRRPTIN RRPTIN XRRPTCTA RRPTCTA XRET_NM.1 RET_NMP \
0 1688.0 R ... R 0.0 R 6.0 R 2.0
1 2294.0 R ... R 0.0 R 42.0 R 20.0
2 2.0 Z ... A NaN A NaN A NaN
3 1489.0 R ... R 0.0 R 8.0 R 2.0
4 1000.0 R ... R 0.0 R 19.0 R 1.0
.. ... ... ... ... ... ... ... ... ...
66 41.0 Z ... A NaN A NaN A NaN
67 2.0 Z ... A NaN A NaN A NaN
68 3.0 R ... A NaN A NaN A NaN
69 99.0 R ... R 0.0 R 0.0 R 0.0
70 19.0 R ... R 0.0 R 0.0 R 0.0
XRET_PCP RET_PCP XSTUFACR STUFACR
0 R 33.0 R 18
1 R 48.0 R 20
2 A NaN R 13
3 R 25.0 R 19
4 R 5.0 R 15
.. ... ... ... ...
66 A NaN R 25
67 A NaN R 4
68 A NaN R 20
69 A NaN R 10
70 A NaN R 24
[71 rows x 33 columns],
104151 R 12427 R.1 17702 R.2 70 R.3 13837 R.4 ... Z.1 0.1 \
0 104160 R 393.0 R 2269.0 R 17.0 R 627.0 R ... R 0.0
1 104179 R 5374.0 R 10018.0 R 54.0 R 6036.0 R ... R 0.0
2 104346 R 324.0 R 2131.0 R 15.0 R 514.0 R ... R 0.0
3 104391 A NaN A NaN A NaN R 56.0 R ... A NaN
4 104425 R 478.0 R 882.0 R 54.0 R 520.0 R ... R 0.0
.. ... .. ... .. ... .. ... .. ... .. ... ... ...
66 107220 A NaN A NaN A NaN R 91.0 R ... A NaN
67 107293 A NaN A NaN A NaN R 17.0 R ... A NaN
68 107318 R 74.0 R 511.0 R 14.0 R 87.0 R ... R 0.0
69 107327 R 193.0 R 467.0 R 41.0 R 260.0 R ... R 0.0
70 107442 A NaN A NaN A NaN R 4.0 R ... A NaN
R.10 124 R.11 62 R.12 50 R.13 18
0 R 1223.0 R 501.0 R 41.0 R 17
1 R 1647.0 R 1101.0 R 67.0 R 15
2 R 862.0 R 274.0 R 32.0 R 15
3 A NaN A NaN A NaN R 18
4 R 197.0 R 53.0 R 27.0 R 17
.. ... ... ... ... ... ... ... ..
66 A NaN A NaN A NaN R 5
67 A NaN A NaN A NaN R 20
68 R 56.0 R 20.0 R 36.0 R 9
69 R 43.0 R 9.0 R 21.0 R 17
70 A NaN A NaN A NaN R 20
[71 rows x 33 columns],
107460 R 247 R.1 388 R.2 64 R.3 351 Z ... Z.3 0.3 \
0 107488 A NaN A NaN A NaN R 172.0 R ... R 0.0
1 107512 R 389.0 R 650.0 R 60.0 R 441.0 R ... Z 0.0
2 107521 R 52.0 R 138.0 R 38.0 R 67.0 R ... R 0.0
3 107549 R 149.0 R 384.0 R 39.0 R 162.0 Z ... Z 0.0
4 107558 R 195.0 R 241.0 R 81.0 R 209.0 R ... A NaN
.. ... .. ... .. ... .. ... .. ... .. ... ... ...
66 110653 R 5742.0 R 8510.0 R 67.0 R 6053.0 R ... R 0.0
67 110662 R 6378.0 R 10173.0 R 63.0 R 5908.0 R ... R 0.0
68 110671 R 4818.0 R 7007.0 R 69.0 R 4743.0 R ... R 0.0
69 110680 R 6423.0 R 9794.0 R 66.0 R 6011.0 R ... R 0.0
70 110705 R 4813.0 R 7330.0 R 66.0 R 4928.0 R ... R 0.0
R.8 38.1 R.9 21 R.10 55 R.11 12
0 R 4.0 R 2.0 R 50.0 R 6
1 R 0.0 R 0.0 A NaN R 12
2 R 26.0 R 5.0 R 19.0 R 14
3 R 40.0 R 13.0 R 33.0 R 14
4 A NaN A NaN A NaN R 16
.. ... ... ... ... ... ... ... ..
66 R 16.0 R 10.0 R 63.0 R 18
67 R 11.0 R 8.0 R 73.0 R 18
68 R 26.0 R 18.0 R 69.0 R 22
69 R 12.0 R 6.0 R 50.0 R 19
70 R 7.0 R 5.0 R 71.0 R 18
[71 rows x 33 columns],
110714 R 4158 R.1 5853 R.2 71 R.3 3700 R.4 ... R.11 0.3 \
0 110778 A NaN A NaN A NaN A NaN A ... A NaN
1 110875 A NaN A NaN A NaN R 10.0 Z ... Z 0.0
2 110918 R 1.0 R 7.0 R 14.0 R 1.0 R ... A NaN
3 111045 R 2.0 R 9.0 R 22.0 R 0.0 R ... R 0.0
4 111054 A NaN A NaN A NaN R 16.0 R ... A NaN
.. ... .. ... .. ... .. ... .. ... .. ... ... ...
66 115010 A NaN A NaN A NaN R 0.0 R ... A NaN
67 115083 A NaN A NaN A NaN A NaN A ... A NaN
68 115126 R 1088.0 R 4298.0 R 25.0 R 1374.0 R ... R 0.0
69 115296 R 1332.0 R 4236.0 R 31.0 R 1693.0 R ... R 0.0
70 115357 A NaN A NaN A NaN R 16.0 Z ... A NaN
R.12 13.1 R.13 7 R.14 54 R.15 25
0 A NaN A NaN A NaN R 9
1 R 20.0 R 8.0 R 40.0 R 11
2 A NaN A NaN A NaN R 2
3 R 0.0 R 0.0 A NaN R 11
4 A NaN A NaN A NaN R 11
.. ... ... ... ... ... ... ... ..
66 A NaN A NaN A NaN R 15
67 A NaN A NaN A NaN R 12
68 R 756.0 R 265.0 R 35.0 R 29
69 R 1000.0 R 392.0 R 39.0 R 24
70 A NaN A NaN A NaN R 15
[71 rows x 33 columns],
115393 R 987 R.1 2580 R.2 38 R.3 1024 R.4 ... R.11 0.3 \
0 115409 R 207.0 R 235.0 R 88.0 R 224.0 R ... A NaN
1 115658 A NaN A NaN A NaN R 8.0 Z ... Z 0.0
2 115728 R 132.0 R 221.0 R 60.0 R 161.0 R ... R 0.0
3 115755 R 532.0 R 1536.0 R 35.0 R 815.0 Z ... Z 0.0
4 115773 R 6.0 R 40.0 R 15.0 R 1.0 R ... R 0.0
.. ... .. ... .. ... .. ... .. ... .. ... ... ...
66 119845 A NaN A NaN A NaN R 11.0 Z ... Z 0.0
67 119951 A NaN A NaN A NaN R 62.0 R ... A NaN
68 120069 A NaN A NaN A NaN R 67.0 R ... A NaN
69 120078 A NaN A NaN A NaN R 54.0 R ... A NaN
70 120087 A NaN A NaN A NaN R 45.0 R ... A NaN
R.12 1450.1 R.13 194 R.14 13 R.15 24
0 A NaN A NaN A NaN R 8.0
1 R 9.0 R 5.0 R 56.0 R 15.0
2 R 1.0 R 1.0 R 100.0 R 7.0
3 R 8.0 R 5.0 R 63.0 R 17.0
4 R 0.0 R 0.0 A NaN R 12.0
.. ... ... ... ... ... ... ... ...
66 R 1.0 R 1.0 R 100.0 R 15.0
67 A NaN A NaN A NaN R 31.0
68 A NaN A NaN A NaN R 15.0
69 A NaN A NaN A NaN R 33.0
70 A NaN A NaN A NaN R 16.0
[71 rows x 33 columns],
120166 R 1 R.1 1.1 R.2 100 R.3 0 R.4 ... R.10 0.7 \
0 120184 A NaN A NaN A NaN A NaN A ... A NaN
1 120254 R 402.0 R 433.0 R 93.0 R 562.0 R ... A NaN
2 120290 R 710.0 R 2523.0 R 28.0 R 777.0 R ... R 0.0
3 120342 R 2101.0 R 5734.0 R 37.0 R 2376.0 R ... R 0.0
4 120403 R 224.0 R 321.0 R 70.0 R 274.0 R ... R 0.0
.. ... .. ... .. ... .. ... .. ... .. ... ... ...
66 123493 A NaN A NaN A NaN R 44.0 R ... A NaN
67 123509 R 318.0 R 3307.0 R 10.0 R 575.0 R ... R 0.0
68 123527 R 942.0 R 3400.0 R 28.0 R 1587.0 R ... R 0.0
69 123554 R 468.0 R 649.0 R 72.0 R 516.0 R ... A NaN
70 123563 R 684.0 R 2511.0 R 27.0 R 0.0 R ... R 0.0
R.11 0.8 R.12 0.9 A.1 Unnamed: 1 R.13 2
0 A NaN A NaN A NaN R 8.0
1 A NaN A NaN A NaN R 8.0
2 R 450.0 R 221.0 R 49.0 R 26.0
3 R 1285.0 R 521.0 R 41.0 R 27.0
4 R 0.0 R 0.0 A NaN R 7.0
.. ... ... ... ... ... ... ... ...
66 A NaN A NaN A NaN R 11.0
67 R 466.0 R 154.0 R 33.0 R 26.0
68 R 1009.0 R 355.0 R 35.0 R 21.0
69 A NaN A NaN A NaN R 9.0
70 R 0.0 R 0.0 A NaN R 25.0
[71 rows x 33 columns],
123572 R 877 R.1 1633 R.2 54 R.3 1531 Z ... Z.3 0.3 R.8 \
0 123642 A NaN A NaN A NaN R 8 R ... R 0.0 R
1 123651 R 551.0 R 687.0 R 80.0 R 481 R ... R 0.0 R
2 123679 A NaN A NaN A NaN R 122 Z ... Z 0.0 R
3 123800 R 1492.0 R 4503.0 R 33.0 R 2089 R ... R 0.0 R
4 123952 R 27.0 R 64.0 R 42.0 R 30 R ... A NaN A
.. ... .. ... .. ... .. ... .. ... .. ... ... ... ...
66 127918 R 481.0 R 739.0 R 65.0 R 481 R ... A NaN A
67 127945 R 75.0 R 351.0 R 21.0 R 80 R ... R 0.0 R
68 127954 A NaN A NaN A NaN R 0 R ... A NaN A
69 128106 R 538.0 R 987.0 R 55.0 R 609 R ... R 0.0 R
70 128151 A NaN A NaN A NaN R 321 R ... R 0.0 R
20.1 R.9 9 R.10 45 R.11 21
0 3.0 R 3.0 R 100.0 R 15
1 4.0 R 4.0 R 100.0 R 16
2 0.0 R 0.0 A NaN R 18
3 1187.0 R 513.0 R 43.0 R 24
4 NaN A NaN A NaN R 15
.. ... ... ... ... ... ... ..
66 NaN A NaN A NaN R 11
67 50.0 R 11.0 R 22.0 R 10
68 NaN A NaN A NaN R 15
69 25.0 R 18.0 R 72.0 R 15
70 12.0 R 9.0 R 75.0 R 20
[71 rows x 33 columns],
128179 A Unnamed: 0 A.1 Unnamed: 1 A.2 Unnamed: 2 R 56 R.1 ... \
0 128188 A NaN A NaN A NaN R 107.0 R ...
1 128258 R 262.0 R 407.0 R 64.0 R 255.0 R ...
2 128328 R 1132.0 R 1132.0 R 100.0 R 1132.0 R ...
3 128337 A NaN A NaN A NaN R 36.0 R ...
4 128391 R 413.0 R 1537.0 R 27.0 R 450.0 R ...
.. ... .. ... .. ... .. ... .. ... .. ...
66 131520 R 2358.0 R 2627.0 R 90.0 R 1920.0 R ...
67 131803 A NaN A NaN A NaN R 0.0 R ...
68 131830 A NaN A NaN A NaN R 3.0 R ...
69 131876 R 221.0 R 386.0 R 57.0 R 233.0 R ...
70 132374 A NaN A NaN A NaN R 962.0 R ...
A.5 Unnamed: 5 A.6 Unnamed: 6 A.7 Unnamed: 7 A.8 Unnamed: 8 R.6 22
0 A NaN A NaN A NaN A NaN R 19
1 R 0.0 R 71.0 R 36.0 R 51.0 R 11
2 A NaN A NaN A NaN A NaN R 6
3 Z 0.0 R 16.0 R 8.0 R 50.0 R 19
4 R 0.0 R 4.0 R 2.0 R 50.0 R 18
.. ... ... ... ... ... ... ... ... ... ..
66 Z 0.0 R 5.0 R 1.0 R 20.0 R 12
67 R 0.0 R 47.0 R 20.0 R 43.0 R 28
68 A NaN A NaN A NaN A NaN R 8
69 Z 0.0 R 12.0 R 3.0 R 25.0 R 11
70 A NaN A NaN A NaN A NaN R 12
[71 rows x 33 columns],
132408 R 26 R.1 169 R.2 15 R.3 20 R.4 ... R.11 0.3 \
0 132471 R 636.0 R 1187.0 R 54.0 R 709.0 R ... R 0.0
1 132602 R 677.0 R 752.0 R 90.0 R 559.0 R ... R 0.0
2 132657 R 669.0 R 841.0 R 80.0 R 725.0 R ... R 0.0
3 132675 A NaN A NaN A NaN R 87.0 R ... R 0.0
4 132693 R 1111.0 R 2379.0 R 47.0 R 0.0 R ... R 0.0
.. ... .. ... .. ... .. ... .. ... .. ... ... ...
66 135647 A NaN A NaN A NaN R 164.0 R ... R 0.0
67 135717 R 6469.0 R 10319.0 R 63.0 R 0.0 R ... Z 0.0
68 135726 R 2339.0 R 3013.0 R 78.0 R 2180.0 R ... R 0.0
69 135735 A NaN A NaN A NaN R 261.0 Z ... Z 0.0
70 136109 A NaN A NaN A NaN R 16.0 Z ... Z 0.0
R.12 5.1 R.13 4 R.14 80 R.15 8
0 R 8.0 R 1.0 R 13.0 R 15
1 R 1.0 R 0.0 R 0.0 R 15
2 R 14.0 R 6.0 R 43.0 R 17
3 R 60.0 R 6.0 R 10.0 R 6
4 R 0.0 R 0.0 A NaN R 17
.. ... ... ... ... ... ... ... ..
66 R 127.0 R 105.0 R 83.0 R 15
67 R 0.0 R 0.0 A NaN R 19
68 R 23.0 R 18.0 R 78.0 R 12
69 R 149.0 R 111.0 R 74.0 R 17
70 R 8.0 R 8.0 R 100.0 R 15
[71 rows x 33 columns],
136145 R 77 R.1 253 R.2 30 R.3 0 R.4 ... Z.1 0.7 R.9 \
0 136172 R 2613.0 R 4125.0 R 63.0 R 2458 R ... R 0.0 R
1 136215 R 1674.0 R 2244.0 R 75.0 R 1510 R ... R 0.0 R
2 136233 R 460.0 R 956.0 R 48.0 R 0 R ... Z 0.0 R
3 136303 A NaN A NaN A NaN R 98 R ... R 0.0 R
4 136330 R 516.0 R 1169.0 R 44.0 R 514 R ... R 0.0 R
.. ... .. ... .. ... .. ... .. ... .. ... ... ... ...
66 139153 R 47.0 R 209.0 R 22.0 R 10 R ... R 0.0 R
67 139199 R 160.0 R 625.0 R 26.0 R 171 Z ... Z 0.0 R
68 139205 R 224.0 R 453.0 R 49.0 R 192 R ... R 0.0 R
69 139250 R 502.0 R 1099.0 R 46.0 R 392 R ... R 0.0 R
70 139278 R 332.0 R 2059.0 R 16.0 R 453 R ... Z 0.0 R
0.8 R.10 0.9 A.1 Unnamed: 1 R.11 19
0 183.0 R 103.0 R 56.0 R 19
1 16.0 R 8.0 R 50.0 R 17
2 0.0 R 0.0 A NaN R 23
3 31.0 R 3.0 R 10.0 R 8
4 6.0 R 3.0 R 50.0 R 12
.. ... ... ... ... ... ... ..
66 16.0 R 8.0 R 50.0 R 11
67 12.0 R 3.0 R 25.0 R 11
68 3.0 R 1.0 R 33.0 R 16
69 46.0 R 24.0 R 52.0 R 21
70 804.0 R 369.0 R 46.0 R 20
[71 rows x 33 columns],
139311 R 690 R.1 2226 R.2 31 R.3 481 R.4 ... R.11 0.3 \
0 139357 R 168.0 R 964.0 R 17.0 R 226.0 R ... Z 0.0
1 139366 R 1229.0 R 2304.0 R 53.0 R 919.0 R ... R 0.0
2 139384 R 443.0 R 2412.0 R 18.0 R 468.0 R ... Z 0.0
3 139393 R 196.0 R 240.0 R 82.0 R 219.0 R ... A NaN
4 139463 R 700.0 R 1354.0 R 52.0 R 534.0 R ... R 0.0
.. ... .. ... .. ... .. ... .. ... .. ... ... ...
66 142115 R 2753.0 R 7002.0 R 39.0 R 2931.0 R ... Z 0.0
67 142179 R 151.0 R 439.0 R 34.0 R 175.0 Z ... Z 0.0
68 142276 R 1233.0 R 3372.0 R 37.0 R 1073.0 R ... Z 0.0
69 142285 R 1394.0 R 2851.0 R 49.0 R 1456.0 R ... Z 0.0
70 142294 R 265.0 R 311.0 R 85.0 R 360.0 R ... Z 0.0
R.12 84.1 R.13 48 R.14 57 R.15 19
0 R 369.0 R 151.0 R 41.0 R 15
1 R 35.0 R 17.0 R 49.0 R 17
2 R 505.0 R 262.0 R 52.0 R 22
3 A NaN A NaN A NaN R 12
4 R 62.0 R 29.0 R 47.0 R 19
.. ... ... ... ... ... ... ... ..
66 R 92.0 R 36.0 R 39.0 R 18
67 R 114.0 R 59.0 R 52.0 R 11
68 R 69.0 R 24.0 R 35.0 R 13
69 R 19.0 R 7.0 R 37.0 R 16
70 R 1.0 R 1.0 R 100.0 R 11
[71 rows x 33 columns],
142328 R 453 R.1 742 R.2 61 R.3 335 R.4 ... R.11 0.3 \
0 142407 A NaN A NaN A NaN R 7.0 Z ... Z 0.0
1 142416 A NaN A NaN A NaN R 9.0 R ... A NaN
2 142443 R 594.0 R 1785.0 R 33.0 R 645.0 R ... R 0.0
3 142461 R 282.0 R 392.0 R 72.0 R 278.0 Z ... A NaN
4 142489 A NaN A NaN A NaN R 18.0 R ... A NaN
.. ... .. ... .. ... .. ... .. ... .. ... ... ...
66 145707 R 200.0 R 479.0 R 42.0 R 227.0 R ... R 0.0
67 145725 R 513.0 R 714.0 R 72.0 R 583.0 R ... R 0.0
68 145813 R 3324.0 R 5056.0 R 66.0 R 3835.0 R ... R 0.0
69 145831 R 404.0 R 1008.0 R 40.0 R 410.0 R ... R 0.0
70 146205 R 502.0 R 1586.0 R 32.0 R 515.0 R ... R 0.0
R.12 23.1 R.13 5 R.14 22 R.15 15
0 R 2.0 R 1.0 R 50.0 R 9
1 A NaN A NaN A NaN R 20
2 R 243.0 R 86.0 R 35.0 R 13
3 A NaN A NaN A NaN R 18
4 A NaN A NaN A NaN R 13
.. ... ... ... ... ... ... ... ..
66 R 20.0 R 9.0 R 45.0 R 11
67 R 0.0 R 0.0 A NaN R 10
68 R 25.0 R 19.0 R 76.0 R 19
69 R 146.0 R 77.0 R 53.0 R 14
70 R 156.0 R 62.0 R 40.0 R 20
[71 rows x 33 columns],
146278 R 333 R.1 924 R.2 36 R.3 391 R.4 ... R.11 0.2 \
0 146296 R 689.0 R 2014.0 R 34.0 R 881.0 R ... R 0.0
1 146339 R 154.0 R 322.0 R 48.0 R 157.0 R ... R 0.0
2 146348 R 263.0 R 743.0 R 35.0 R 280.0 R ... R 0.0
3 146366 R 305.0 R 1745.0 R 17.0 R 239.0 R ... R 0.0
4 146418 R 319.0 R 1181.0 R 27.0 R 387.0 R ... R 0.0
.. ... .. ... .. ... .. ... .. ... .. ... ... ...
66 149222 R 1322.0 R 2646.0 R 50.0 R 928.0 R ... R 0.0
67 149231 R 1509.0 R 2729.0 R 55.0 R 1645.0 R ... R 0.0
68 149310 A NaN A NaN A NaN R 38.0 R ... A NaN
69 149329 R 22.0 R 22.0 R 100.0 R 19.0 R ... A NaN
70 149365 R 157.0 R 1260.0 R 12.0 R 203.0 R ... R 0.0
R.12 128 R.13 66 R.14 52 R.15 13
0 R 579.0 R 233.0 R 40.0 R 15
1 R 0.0 R 0.0 A NaN R 10
2 R 142.0 R 68.0 R 48.0 R 12
3 R 60.0 R 25.0 R 42.0 R 17
4 R 129.0 R 39.0 R 30.0 R 16
.. ... ... ... ... ... ... ... ..
66 R 12.0 R 3.0 R 25.0 R 11
67 R 22.0 R 7.0 R 32.0 R 16
68 A NaN A NaN A NaN R 8
69 A NaN A NaN A NaN R 13
70 R 173.0 R 59.0 R 34.0 R 12
[71 rows x 33 columns],
149499 A Unnamed: 0 A.1 Unnamed: 1 A.2 Unnamed: 2 R 7 R.1 ... \
0 149505 R 178.0 R 294.0 R 61.0 R 160.0 R ...
1 149514 R 100.0 R 192.0 R 52.0 R 102.0 R ...
2 149532 R 759.0 R 2826.0 R 27.0 R 827.0 R ...
3 149550 A NaN A NaN A NaN R 35.0 R ...
4 149639 R 9.0 R 18.0 R 50.0 R 15.0 Z ...
.. ... .. ... .. ... .. ... .. ... .. ...
66 152600 R 635.0 R 783.0 R 81.0 R 646.0 R ...
67 152628 A NaN A NaN A NaN R 14.0 R ...
68 152637 R 1278.0 R 8416.0 R 15.0 R 25.0 R ...
69 152673 R 240.0 R 249.0 R 96.0 R 229.0 R ...
70 152798 A NaN A NaN A NaN R 0.0 R ...
A.5 Unnamed: 5 A.6 Unnamed: 6 A.7 Unnamed: 7 A.8 Unnamed: 8 R.6 7.2
0 A NaN A NaN A NaN A NaN R 10
1 R 0.0 R 2.0 R 0.0 R 0.0 R 8
2 R 0.0 R 347.0 R 126.0 R 36.0 R 18
3 R 0.0 R 7.0 R 5.0 R 71.0 R 11
4 A NaN A NaN A NaN A NaN R 4
.. ... ... ... ... ... ... ... ... ... ..
66 R 0.0 R 0.0 R 0.0 A NaN R 11
67 R 0.0 R 5.0 R 2.0 R 40.0 R 10
68 R 0.0 R 3.0 R 2.0 R 67.0 R 20
69 A NaN A NaN A NaN A NaN R 9
70 R 0.0 R 0.0 R 0.0 A NaN R 11
[71 rows x 33 columns],
152992 R 172 R.1 364 R.2 47 R.3 136 R.4 ... A.2 \
0 153001 R 229.0 R 427.0 R 54.0 R 230.0 R ... R
1 153074 A NaN A NaN A NaN R 19.0 R ... A
2 153083 A NaN A NaN A NaN R 17.0 R ... A
3 153108 R 324.0 R 377.0 R 86.0 R 337.0 R ... R
4 153126 R 146.0 R 210.0 R 70.0 R 134.0 R ... R
.. ... .. ... .. ... .. ... .. ... .. ... ...
66 154590 R 331.0 R 491.0 R 67.0 R 363.0 R ... R
67 154642 R 331.0 R 1020.0 R 32.0 R 351.0 R ... R
68 154688 R 219.0 R 334.0 R 66.0 R 244.0 R ... R
69 154697 R 408.0 R 1621.0 R 25.0 R 397.0 R ... R
70 154712 R 575.0 R 772.0 R 74.0 R 524.0 R ... R
Unnamed: 2 A.3 Unnamed: 3 A.4 Unnamed: 4 A.5 Unnamed: 5 R.9 11
0 0.0 R 0.0 R 0.0 A NaN R 10
1 NaN A NaN A NaN A NaN R 9
2 NaN A NaN A NaN A NaN R 10
3 0.0 R 0.0 R 0.0 A NaN R 11
4 0.0 R 0.0 R 0.0 A NaN R 8
.. ... ... ... ... ... ... ... ... ..
66 0.0 R 0.0 R 0.0 A NaN R 15
67 0.0 R 116.0 R 34.0 R 29.0 R 20
68 0.0 R 1.0 R 1.0 R 100.0 R 10
69 0.0 R 196.0 R 45.0 R 23.0 R 18
70 0.0 R 0.0 R 0.0 A NaN R 13
[71 rows x 33 columns],
154721 R 221 R.1 325 R.2 68 R.3 245 R.4 ... R.11 0.4 \
0 154749 R 151.0 R 207.0 R 73.0 R 155.0 R ... R 0.0
1 154800 R 1178.0 R 2313.0 R 51.0 R 1259.0 R ... R 0.0
2 154855 A NaN A NaN A NaN R 85.0 R ... R 0.0
3 154907 R 168.0 R 630.0 R 27.0 R 375.0 Z ... R 0.0
4 154925 R 385.0 R 665.0 R 58.0 R 469.0 R ... R 0.0
.. ... .. ... .. ... .. ... .. ... .. ... ... ...
66 156417 R 7.0 R 16.0 R 44.0 R 17.0 R ... R 0.0
67 156426 A NaN A NaN A NaN R 8.0 Z ... Z 0.0
68 156471 A NaN A NaN A NaN R 27.0 R ... R 0.0
69 156541 R 590.0 R 1514.0 R 39.0 R 741.0 R ... R 0.0
70 156620 R 2165.0 R 3763.0 R 58.0 R 1905.0 R ... Z 0.0
R.12 0.5 R.13 0.6 A Unnamed: 0 R.14 14
0 R 0.0 R 0.0 A NaN R 10
1 R 487.0 R 166.0 R 34.0 R 17
2 R 1.0 R 1.0 R 100.0 R 17
3 R 23.0 R 8.0 R 35.0 R 14
4 R 12.0 R 6.0 R 50.0 R 21
.. ... ... ... ... .. ... ... ..
66 R 1.0 R 1.0 R 100.0 R 9
67 R 27.0 R 23.0 R 85.0 R 20
68 R 1.0 R 0.0 R 0.0 R 14
69 R 15.0 R 3.0 R 20.0 R 20
70 R 31.0 R 14.0 R 45.0 R 15
[71 rows x 33 columns],
156648 R 639 R.1 1389 R.2 46 R.3 767 R.4 ... R.11 0.2 \
0 156745 R 426.0 R 482.0 R 88.0 R 314.0 R ... R 0.0
1 156754 A NaN A NaN A NaN R 2.0 R ... A NaN
2 156790 R 258.0 R 436.0 R 59.0 R 350.0 R ... R 0.0
3 156842 A NaN A NaN A NaN R 5.0 Z ... Z 0.0
4 156851 R 151.0 R 251.0 R 60.0 R 186.0 R ... R 0.0
.. ... .. ... .. ... .. ... .. ... .. ... ... ...
66 159647 R 1858.0 R 3474.0 R 53.0 R 1967.0 R ... R 0.0
67 159656 R 765.0 R 975.0 R 78.0 R 822.0 R ... R 0.0
68 159717 R 1194.0 R 2191.0 R 54.0 R 1202.0 R ... R 0.0
69 159939 R 1078.0 R 2387.0 R 45.0 R 926.0 R ... R 0.0
70 159948 R 18.0 R 184.0 R 10.0 R 18.0 R ... R 0.0
R.12 325.1 R.13 116 R.14 36 R.15 22
0 R 0.0 R 0.0 A NaN R 12
1 A NaN A NaN A NaN R 13
2 R 54.0 R 34.0 R 63.0 R 15
3 R 42.0 R 33.0 R 79.0 R 17
4 R 66.0 R 30.0 R 45.0 R 15
.. ... ... ... ... ... ... ... ..
66 R 6.0 R 1.0 R 17.0 R 23
67 R 8.0 R 3.0 R 38.0 R 13
68 R 13.0 R 6.0 R 46.0 R 21
69 R 9.0 R 3.0 R 33.0 R 20
70 R 51.0 R 15.0 R 29.0 R 15
[71 rows x 33 columns],
159966 R 1189 R.1 1847 R.2 64 R.3 1169 R.4 ... R.11 0.2 \
0 159993 R 1123.0 R 2371.0 R 47.0 R 1123 R ... R 0.0
1 160010 R 125.0 R 357.0 R 35.0 R 132 R ... R 0.0
2 160038 R 1401.0 R 3523.0 R 40.0 R 1312 R ... R 0.0
3 160065 R 52.0 R 308.0 R 17.0 R 61 R ... R 0.0
4 160074 R 82.0 R 299.0 R 27.0 R 59 R ... R 0.0
.. ... .. ... .. ... .. ... .. ... .. ... ... ...
66 162557 R 664.0 R 1377.0 R 48.0 R 785 R ... R 0.0
67 162584 R 627.0 R 980.0 R 64.0 R 739 R ... Z 0.0
68 162609 R 145.0 R 284.0 R 51.0 R 197 R ... R 0.0
69 162654 R 232.0 R 256.0 R 91.0 R 338 R ... R 0.0
70 162690 R 440.0 R 1188.0 R 37.0 R 534 R ... R 0.0
R.12 6.1 R.13 3 R.14 50 R.15 19
0 R 20.0 R 11.0 R 55.0 R 18
1 R 130.0 R 49.0 R 38.0 R 8
2 R 67.0 R 27.0 R 40.0 R 19
3 R 1.0 R 0.0 R 0.0 R 10
4 R 2.0 R 1.0 R 50.0 R 10
.. ... ... ... ... ... ... ... ..
66 R 343.0 R 154.0 R 45.0 R 17
67 R 1.0 R 0.0 R 0.0 R 14
68 R 5.0 R 3.0 R 60.0 R 13
69 R 0.0 Z 0.0 A NaN R 9
70 R 284.0 R 131.0 R 46.0 R 18
[71 rows x 33 columns],
162706 R 696 R.1 1312 R.2 53 R.3 736 R.4 ... R.11 0.3 \
0 162760 R 293.0 R 387.0 R 76.0 R 320.0 R ... R 0.0
1 162779 R 751.0 R 1917.0 R 39.0 R 962.0 R ... R 0.0
2 162830 A NaN A NaN A NaN R 41.0 Z ... A NaN
3 162928 R 1404.0 R 1759.0 R 80.0 R 1475.0 R ... A NaN
4 163028 A NaN A NaN A NaN R 162.0 R ... R 0.0
.. ... .. ... .. ... .. ... .. ... .. ... ... ...
66 165644 R 123.0 R 169.0 R 73.0 R 131.0 R ... Z 0.0
67 165662 R 938.0 R 1149.0 R 82.0 R 940.0 Z ... Z 0.0
68 165671 R 419.0 R 473.0 R 89.0 R 582.0 R ... A NaN
69 165699 R 769.0 R 916.0 R 84.0 R 846.0 R ... R 0.0
70 165750 A NaN A NaN A NaN R 3.0 R ... A NaN
R.12 322.1 R.13 138 R.14 43 R.15 17
0 R 0.0 Z 0.0 A NaN R 11
1 R 661.0 R 297.0 R 45.0 R 15
2 A NaN A NaN A NaN R 15
3 A NaN A NaN A NaN R 6
4 R 14.0 R 13.0 R 93.0 R 20
.. ... ... ... ... ... ... ... ..
66 R 0.0 Z 0.0 A NaN R 10
67 R 2.0 R 2.0 R 100.0 R 13
68 A NaN A NaN A NaN R 13
69 R 0.0 R 0.0 A NaN R 13
70 A NaN A NaN A NaN R 10
[71 rows x 33 columns],
165802 R 183 R.1 331 R.2 55 R.3 157 Z ... Z.3 0.4 \
0 165820 R 652.0 R 1039.0 R 63.0 R 671.0 R ... R 0.0
1 165866 R 608.0 R 959.0 R 63.0 R 772.0 R ... R 0.0
2 165884 R 112.0 R 216.0 R 52.0 R 5.0 R ... R 0.0
3 165936 R 373.0 R 404.0 R 92.0 R 355.0 R ... R 0.0
4 165981 R 106.0 R 660.0 R 16.0 R 130.0 R ... R 0.0
.. ... .. ... .. ... .. ... .. ... .. ... ... ...
66 168421 R 1294.0 R 1352.0 R 96.0 R 1199.0 R ... A NaN
67 168430 R 799.0 R 1184.0 R 67.0 R 878.0 R ... R 0.0
68 168528 R 535.0 R 611.0 R 88.0 R 540.0 R ... R 0.0
69 168546 R 476.0 R 523.0 R 91.0 R 415.0 R ... Z 0.0
70 168555 A NaN A NaN A NaN R 14.0 R ... R 0.0
R.8 0.5 Z.4 0.6 A Unnamed: 0 R.9 11
0 R 2.0 R 1.0 R 50.0 R 14
1 R 4.0 R 0.0 R 0.0 R 13
2 R 1.0 R 0.0 R 0.0 R 9
3 R 3.0 R 1.0 R 33.0 R 10
4 R 169.0 R 79.0 R 47.0 R 12
.. ... ... ... ... .. ... ... ..
66 A NaN A NaN A NaN R 13
67 R 8.0 R 4.0 R 50.0 R 16
68 R 1.0 R 0.0 R 0.0 R 14
69 R 0.0 Z 0.0 A NaN R 12
70 R 3.0 R 2.0 R 67.0 R 7
[71 rows x 33 columns],
168573 A Unnamed: 0 A.1 Unnamed: 1 A.2 Unnamed: 2 A.3 Unnamed: 3 A.4 \
0 168591 R 396.0 R 454.0 R 87.0 R 384 R
1 168607 R 201.0 R 537.0 R 37.0 R 246 R
2 168740 R 250.0 R 354.0 R 71.0 R 279 R
3 168786 R 278.0 R 446.0 R 62.0 R 257 R
4 168847 R 347.0 R 1703.0 R 20.0 R 170 R
.. ... .. ... .. ... .. ... .. ... ..
66 171535 R 1571.0 R 6722.0 R 23.0 R 1044 R
67 171571 R 2213.0 R 3971.0 R 56.0 R 2633 R
68 171599 R 290.0 R 452.0 R 64.0 R 338 R
69 171775 A NaN A NaN A NaN R 5 R
70 171881 R 17.0 R 59.0 R 29.0 R 11 R
... A.11 Unnamed: 11 A.12 Unnamed: 12 A.13 Unnamed: 13 A.14 \
0 ... R 0.0 R 3.0 R 0.0 R
1 ... R 0.0 R 83.0 R 37.0 R
2 ... R 0.0 R 3.0 R 2.0 R
3 ... R 0.0 R 5.0 R 1.0 R
4 ... R 0.0 R 82.0 R 30.0 R
.. ... ... ... ... ... ... ... ...
66 ... R 0.0 R 1288.0 R 741.0 R
67 ... R 0.0 R 34.0 R 23.0 R
68 ... R 0.0 R 1.0 R 1.0 R
69 ... R 0.0 R 5.0 R 5.0 R
70 ... R 0.0 R 7.0 R 1.0 R
Unnamed: 14 R 25
0 0.0 R 13
1 45.0 R 13
2 67.0 R 10
3 20.0 R 11
4 37.0 R 8
.. ... .. ..
66 58.0 R 23
67 68.0 R 19
68 100.0 R 15
69 100.0 R 13
70 14.0 R 9
[71 rows x 33 columns],
171988 A Unnamed: 0 A.1 Unnamed: 1 A.2 Unnamed: 2 R 34 R.1 ... \
0 171997 A NaN A NaN A NaN R 61.0 R ...
1 172015 A NaN A NaN A NaN R 54.0 R ...
2 172033 R 2.0 R 17.0 R 12.0 R 2.0 R ...
3 172051 R 1350.0 R 1821.0 R 74.0 R 1458.0 R ...
4 172200 R 649.0 R 2700.0 R 24.0 R 0.0 R ...
.. ... .. ... .. ... .. ... .. ... .. ...
66 174437 R 206.0 R 326.0 R 63.0 R 245.0 R ...
67 174473 R 289.0 R 1202.0 R 24.0 R 344.0 R ...
68 174491 R 361.0 R 1591.0 R 23.0 R 399.0 R ...
69 174507 R 10.0 R 127.0 R 8.0 R 0.0 R ...
70 174525 R 24.0 R 54.0 R 44.0 R 7.0 R ...
A.5 Unnamed: 5 A.6 Unnamed: 6 A.7 Unnamed: 7 A.8 Unnamed: 8 R.5 18
0 A NaN A NaN A NaN A NaN R 22
1 A NaN A NaN A NaN A NaN R 23
2 R 0.0 R 10.0 R 6.0 R 60.0 R 8
3 R 0.0 R 12.0 R 8.0 R 67.0 R 17
4 R 0.0 R 0.0 R 0.0 A NaN R 21
.. ... ... ... ... ... ... ... ... ... ..
66 R 0.0 R 0.0 R 0.0 A NaN R 15
67 R 0.0 R 80.0 R 37.0 R 46.0 R 18
68 R 0.0 R 5.0 R 4.0 R 80.0 R 18
69 A NaN A NaN A NaN A NaN R 7
70 R 0.0 R 0.0 R 0.0 A NaN R 10
[71 rows x 33 columns],
174570 R 94 R.1 1016 R.2 9 R.3 120 R.4 ... R.11 0.3 \
0 174604 R 44.0 R 98.0 R 45.0 R 45.0 R ... R 0.0
1 174738 R 588.0 R 2231.0 R 26.0 R 637.0 R ... R 0.0
2 174747 R 400.0 R 427.0 R 94.0 R 438.0 R ... A NaN
3 174756 R 369.0 R 1565.0 R 24.0 R 495.0 R ... R 0.0
4 174783 R 939.0 R 3823.0 R 25.0 R 1200.0 R ... R 0.0
.. ... .. ... .. ... .. ... .. ... .. ... ... ...
66 176798 A NaN A NaN A NaN R 20.0 R ... R 0.0
67 176910 R 30.0 R 48.0 R 63.0 R 37.0 R ... R 0.0
68 176947 R 343.0 R 434.0 R 79.0 R 318.0 R ... R 0.0
69 176965 R 1063.0 R 2120.0 R 50.0 R 1227.0 R ... R 0.0
70 176983 A NaN A NaN A NaN R 43.0 R ... R 0.0
R.12 29.1 R.13 14 R.14 48.1 R.15 25
0 R 4.0 R 1.0 R 25.0 R 18
1 R 243.0 R 123.0 R 51.0 R 22
2 A NaN A NaN A NaN R 12
3 R 296.0 R 150.0 R 51.0 R 21
4 R 24.0 R 12.0 R 50.0 R 19
.. ... ... ... ... ... ... ... ..
66 R 45.0 R 37.0 R 82.0 R 12
67 R 0.0 R 0.0 A NaN R 8
68 R 3.0 R 1.0 R 33.0 R 12
69 R 22.0 R 9.0 R 41.0 R 15
70 R 8.0 R 8.0 R 100.0 R 3
[71 rows x 33 columns],
177038 R 2 R.1 37 R.2 5 R.3 1 R.4 ... Z.1 0.6 \
0 177065 R 264.0 R 1681.0 R 16.0 R 212.0 R ... R 0.0
1 177083 R 3.0 R 10.0 R 30.0 R 4.0 R ... A NaN
2 177117 R 102.0 R 122.0 R 84.0 R 92.0 R ... R 0.0
3 177135 R 793.0 R 1212.0 R 65.0 R 788.0 R ... R 0.0
4 177144 R 254.0 R 345.0 R 74.0 R 254.0 R ... R 0.0
.. ... .. ... .. ... .. ... .. ... .. ... ... ...
66 179566 R 2482.0 R 7410.0 R 33.0 R 2641.0 R ... R 0.0
67 179645 R 534.0 R 1143.0 R 47.0 R 530.0 R ... R 0.0
68 179715 R 327.0 R 482.0 R 68.0 R 326.0 R ... R 0.0
69 179867 R 1801.0 R 2221.0 R 81.0 R 1730.0 R ... R 0.0
70 179894 R 397.0 R 652.0 R 61.0 R 387.0 R ... R 0.0
R.10 0.7 Z.2 0.8 A Unnamed: 0 R.11 7
0 R 144.0 R 39.0 R 27.0 R 23
1 A NaN A NaN A NaN R 4
2 R 0.0 R 0.0 A NaN R 6
3 R 156.0 R 56.0 R 36.0 R 13
4 R 2.0 R 2.0 R 100.0 R 14
.. ... ... ... ... .. ... ... ..
66 R 38.0 R 10.0 R 26.0 R 20
67 R 160.0 R 62.0 R 39.0 R 19
68 R 58.0 R 31.0 R 53.0 R 19
69 R 2.0 R 1.0 R 50.0 R 7
70 R 10.0 R 6.0 R 60.0 R 12
[71 rows x 33 columns],
179946 R 177 R.1 214 R.2 83 R.3 142 R.4 ... A.2 \
0 179955 R 195.0 R 245.0 R 80.0 R 167.0 Z ... Z
1 179964 R 158.0 R 298.0 R 53.0 R 155.0 R ... R
2 179991 A NaN A NaN A NaN R 21.0 R ... A
3 180054 R 66.0 R 114.0 R 58.0 R 77.0 R ... R
4 180063 A NaN A NaN A NaN R 17.0 R ... A
.. ... .. ... .. ... .. ... .. ... .. ... ...
66 182500 R 891.0 R 2030.0 R 44.0 R 0.0 R ... R
67 182564 R 329.0 R 846.0 R 39.0 R 0.0 R ... R
68 182634 R 233.0 R 313.0 R 74.0 R 234.0 R ... R
69 182652 A NaN A NaN A NaN R 15.0 R ... A
70 182670 R 1057.0 R 1124.0 R 94.0 R 1190.0 R ... A
Unnamed: 2 A.3 Unnamed: 3 A.4 Unnamed: 4 A.5 Unnamed: 5 R.9 10
0 0.0 R 1.0 R 0.0 R 0.0 R 10
1 0.0 R 6.0 R 1.0 R 17.0 R 10
2 NaN A NaN A NaN A NaN R 17
3 0.0 R 6.0 R 4.0 R 67.0 R 29
4 NaN A NaN A NaN A NaN R 6
.. ... ... ... ... ... ... ... ... ..
66 0.0 R 0.0 Z 0.0 A NaN R 21
67 0.0 R 0.0 R 0.0 A NaN R 18
68 0.0 R 0.0 R 0.0 A NaN R 12
69 NaN A NaN A NaN A NaN R 11
70 NaN A NaN A NaN A NaN R 7
[71 rows x 33 columns],
182704 A Unnamed: 0 A.1 Unnamed: 1 A.2 Unnamed: 2 R 1 R.1 ... \
0 182722 A NaN A NaN A NaN R 13.0 R ...
1 182795 R 389.0 R 420.0 R 93.0 R 416.0 R ...
2 182892 A NaN A NaN A NaN R 36.0 R ...
3 182917 R 20.0 R 22.0 R 91.0 R 31.0 R ...
4 182953 A NaN A NaN A NaN R 35.0 R ...
.. ... .. ... .. ... .. ... .. ... .. ...
66 185536 R 1647.0 R 3111.0 R 53.0 R 1977.0 R ...
67 185572 R 921.0 R 1135.0 R 81.0 R 994.0 R ...
68 185590 R 3125.0 R 4588.0 R 68.0 R 3082.0 R ...
69 185679 A NaN A NaN A NaN R 3.0 Z ...
70 185721 R 120.0 R 189.0 R 63.0 R 124.0 R ...
A.5 Unnamed: 5 A.6 Unnamed: 6 A.7 Unnamed: 7 A.8 Unnamed: 8 R.6 10
0 R 0.0 R 5.0 R 4.0 R 80.0 R 16
1 R 0.0 R 0.0 R 0.0 A NaN R 12
2 R 0.0 R 8.0 R 7.0 R 88.0 R 12
3 A NaN A NaN A NaN A NaN R 10
4 R 0.0 R 42.0 R 36.0 R 86.0 R 10
.. ... ... ... ... ... ... ... ... ... ..
66 Z 0.0 R 707.0 R 318.0 R 45.0 R 21
67 R 0.0 R 0.0 R 0.0 A NaN R 12
68 R 0.0 R 19.0 R 12.0 R 63.0 R 18
69 Z 0.0 R 1.0 R 1.0 R 100.0 R 10
70 Z 0.0 R 35.0 R 24.0 R 69.0 R 15
[71 rows x 33 columns],
185767 A Unnamed: 0 A.1 Unnamed: 1 A.2 Unnamed: 2 R 3 R.1 ... \
0 185828 R 1129.0 R 2759.0 R 41.0 R 1299.0 R ...
1 185873 R 1481.0 R 2806.0 R 53.0 R 1630.0 R ...
2 185970 A NaN A NaN A NaN R 18.0 R ...
3 186016 A NaN A NaN A NaN R 29.0 Z ...
4 186034 R 291.0 R 739.0 R 39.0 R 617.0 R ...
.. ... .. ... .. ... .. ... .. ... .. ...
66 188669 A NaN A NaN A NaN R 35.0 R ...
67 188678 R 56.0 R 66.0 R 85.0 R 124.0 R ...
68 188687 R 15.0 R 124.0 R 12.0 R 16.0 Z ...
69 188696 A NaN A NaN A NaN R 66.0 Z ...
70 188854 R 416.0 R 485.0 R 86.0 R 163.0 Z ...
R.8 0.3 R.9 6.1 R.10 5 R.11 83 R.12 24
0 Z 0.0 R 44.0 R 30.0 R 68.0 R 15
1 R 0.0 R 389.0 R 158.0 R 41.0 R 18
2 R 0.0 R 3.0 R 1.0 R 33.0 R 12
3 Z 0.0 R 12.0 R 10.0 R 83.0 R 15
4 R 0.0 R 363.0 R 159.0 R 44.0 R 19
.. ... ... ... ... ... ... ... ... ... ..
66 A NaN A NaN A NaN A NaN R 3
67 A NaN A NaN A NaN A NaN R 8
68 Z 0.0 R 33.0 R 15.0 R 45.0 R 22
69 A NaN A NaN A NaN A NaN R 18
70 A NaN A NaN A NaN A NaN R 5
[71 rows x 33 columns],
188890 A Unnamed: 0 A.1 Unnamed: 1 A.2 Unnamed: 2 R 659 R.1 ... \
0 188915 A NaN A NaN A NaN R 1.0 R ...
1 188942 R 96.0 R 192.0 R 50.0 R 68.0 R ...
2 189088 R 363.0 R 574.0 R 63.0 R 482.0 R ...
3 189097 R 676.0 R 823.0 R 82.0 R 624.0 R ...
4 189219 A NaN A NaN A NaN A NaN A ...
.. ... .. ... .. ... .. ... .. ... .. ...
66 190983 R 173.0 R 201.0 R 86.0 R 217.0 R ...
67 191083 R 1479.0 R 2911.0 R 51.0 R 1770.0 Z ...
68 191126 R 1247.0 R 1956.0 R 64.0 R 1383.0 R ...
69 191199 R 898.0 R 1437.0 R 62.0 R 944.0 Z ...
70 191205 R 154.0 R 205.0 R 75.0 R 129.0 R ...
Z.2 0.2 R.6 258.1 R.7 175 R.8 68 R.9 18
0 A NaN A NaN A NaN A NaN R 4
1 A NaN A NaN A NaN A NaN R 19
2 A NaN A NaN A NaN A NaN R 9
3 R 0.0 R 8.0 R 8.0 R 100.0 R 9
4 A NaN A NaN A NaN A NaN R 16
.. ... ... ... ... ... ... ... ... ... ..
66 A NaN A NaN A NaN A NaN R 10
67 Z 0.0 R 218.0 R 76.0 R 35.0 R 17
68 R 0.0 R 20.0 R 12.0 R 60.0 R 17
69 Z 0.0 R 81.0 R 38.0 R 47.0 R 23
70 R 0.0 R 2.0 R 1.0 R 50.0 R 10
[71 rows x 33 columns],
191241 R 2071 R.1 2463 R.2 84 R.3 2260 R.4 ... R.11 0.3 \
0 191287 A NaN A NaN A NaN A NaN A ... A NaN
1 191302 R 294.0 R 364.0 R 81.0 R 416.0 Z ... Z 0.0
2 191311 A NaN A NaN A NaN A NaN A ... A NaN
3 191339 R 532.0 R 967.0 R 55.0 R 655.0 Z ... Z 0.0
4 191515 R 438.0 R 450.0 R 97.0 R 473.0 R ... A NaN
.. ... .. ... .. ... .. ... .. ... .. ... ... ...
66 193973 R 623.0 R 748.0 R 83.0 R 626.0 R ... Z 0.0
67 193991 A NaN A NaN A NaN R 5.0 R ... Z 0.0
68 194028 R 197.0 R 598.0 R 33.0 R 280.0 Z ... Z 0.0
69 194091 R 687.0 R 929.0 R 74.0 R 816.0 R ... R 0.0
70 194116 R 13.0 R 176.0 R 7.0 R 6.0 Z ... Z 0.0
R.12 10.1 R.13 6 R.14 60 R.15 13
0 A NaN A NaN A NaN P 10
1 R 63.0 R 31.0 R 49.0 R 22
2 A NaN A NaN A NaN R 5
3 R 65.0 R 32.0 R 49.0 R 15
4 A NaN A NaN A NaN R 9
.. ... ... ... ... ... ... ... ..
66 R 0.0 R 0.0 A NaN R 11
67 R 1.0 R 1.0 R 100.0 R 11
68 R 23.0 R 11.0 R 48.0 R 14
69 R 33.0 R 5.0 R 15.0 R 11
70 R 0.0 Z 0.0 A NaN R 11
[71 rows x 33 columns],
194161 R 116 R.1 498 R.2 23 R.3 83 R.4 ... R.11 0.3 \
0 194189 R 1.0 R 1.0 R 100.0 R 0.0 R ... A NaN
1 194222 R 1347.0 R 2161.0 R 62.0 R 1647.0 Z ... Z 0.0
2 194240 R 920.0 R 1463.0 R 63.0 R 913.0 Z ... Z 0.0
3 194259 A NaN A NaN A NaN R 19.0 R ... A NaN
4 194310 R 1773.0 R 2290.0 R 77.0 R 1915.0 R ... R 0.0
.. ... .. ... .. ... .. ... .. ... .. ... ... ...
66 196264 R 102.0 R 2219.0 R 5.0 R 57.0 R ... R 0.0
67 196291 R 341.0 R 436.0 R 78.0 R 344.0 Z ... Z 0.0
68 196307 A NaN A NaN A NaN A NaN A ... A NaN
69 196389 R 78.0 R 181.0 R 43.0 R 325.0 R ... R 0.0
70 196413 R 3486.0 R 3877.0 R 90.0 R 3641.0 R ... Z 0.0
R.12 6.1 R.13 1 R.14 17 R.15 16
0 A NaN A NaN A NaN R 15
1 R 169.0 R 40.0 R 24.0 R 19
2 R 211.0 R 110.0 R 52.0 R 18
3 A NaN A NaN A NaN R 13
4 R 31.0 R 18.0 R 58.0 R 14
.. ... ... ... ... ... ... ... ..
66 R 19.0 R 9.0 R 47.0 R 18
67 R 1.0 R 0.0 R 0.0 R 16
68 A NaN A NaN A NaN R 6
69 R 14.0 R 2.0 R 14.0 R 12
70 R 19.0 R 7.0 R 37.0 R 15
[71 rows x 33 columns],
196431 R 42 R.1 227 R.2 19 R.3 50 R.4 ... A.2 \
0 196440 R 2.0 R 2.0 R 100.0 R 3.0 R ... A
1 196565 R 337.0 R 562.0 R 60.0 R 537.0 R ... Z
2 196583 R 3.0 R 25.0 R 12.0 R 7.0 R ... A
3 196592 R 526.0 R 1771.0 R 30.0 R 340.0 Z ... Z
4 196653 R 88.0 R 416.0 R 21.0 R 1.0 R ... R
.. ... .. ... .. ... .. ... .. ... .. ... ...
66 198561 R 470.0 R 728.0 R 65.0 R 401.0 R ... Z
67 198570 R 242.0 R 2087.0 R 12.0 R 296.0 R ... R
68 198598 R 133.0 R 227.0 R 59.0 R 181.0 R ... A
69 198613 R 372.0 R 461.0 R 81.0 R 380.0 R ... R
70 198622 R 862.0 R 3781.0 R 23.0 R 932.0 R ... R
Unnamed: 2 A.3 Unnamed: 3 A.4 Unnamed: 4 A.5 Unnamed: 5 R.9 14
0 NaN A NaN A NaN A NaN R 8
1 0.0 R 39.0 R 16.0 R 41.0 R 11
2 NaN A NaN A NaN A NaN R 9
3 0.0 R 36.0 R 21.0 R 58.0 R 11
4 0.0 R 0.0 R 0.0 A NaN R 11
.. ... ... ... ... ... ... ... ... ..
66 0.0 R 0.0 Z 0.0 A NaN R 13
67 0.0 R 1427.0 R 701.0 R 49.0 R 11
68 NaN A NaN A NaN A NaN R 8
69 0.0 R 0.0 R 0.0 A NaN R 12
70 0.0 R 898.0 R 369.0 R 41.0 R 18
[71 rows x 33 columns],
198640 R 29 R.1 329 R.2 9 R.3 128 R.4 ... R.11 0.3 \
0 198668 R 170.0 R 570.0 R 30.0 R 203.0 R ... R 0.0
1 198677 R 1.0 R 4.0 R 25.0 R 0.0 Z ... Z 0.0
2 198695 R 1387.0 R 1470.0 R 94.0 R 1400.0 R ... A NaN
3 198710 R 199.0 R 739.0 R 27.0 R 200.0 R ... R 0.0
4 198729 R 72.0 R 373.0 R 19.0 R 75.0 Z ... Z 0.0
.. ... .. ... .. ... .. ... .. ... .. ... ... ...
66 199847 R 1452.0 R 1472.0 R 99.0 R 1359.0 R ... R 0.0
67 199856 R 1700.0 R 7170.0 R 24.0 R 2085.0 R ... R 0.0
68 199865 R 194.0 R 226.0 R 86.0 R 235.0 R ... A NaN
69 199883 A NaN A NaN A NaN A NaN A ... A NaN
70 199892 R 152.0 R 374.0 R 41.0 R 281.0 R ... R 0.0
R.12 33.1 R.13 10 R.14 30 R.15 11
0 R 57.0 R 28.0 R 49.0 R 8
1 R 0.0 Z 0.0 A NaN R 5
2 A NaN A NaN A NaN R 17
3 R 113.0 R 68.0 R 60.0 R 12
4 R 53.0 R 22.0 R 42.0 R 9
.. ... ... ... ... ... ... ... ..
66 R 1.0 R 1.0 R 100.0 R 11
67 R 1819.0 R 926.0 R 51.0 R 18
68 A NaN A NaN A NaN R 9
69 A NaN A NaN A NaN R 11
70 R 163.0 R 84.0 R 52.0 R 12
[71 rows x 33 columns],
199908 R 74 R.1 561 R.2 13 R.3 122 R.4 ... R.11 0.3 \
0 199926 R 294.0 R 812.0 R 36.0 R 342.0 R ... R 0.0
1 199953 R 86.0 R 438.0 R 20.0 R 93.0 R ... R 0.0
2 199962 R 815.0 R 897.0 R 91.0 R 942.0 R ... R 0.0
3 199971 R 34.0 R 38.0 R 89.0 R 10.0 R ... A NaN
4 199980 A NaN A NaN A NaN R 32.0 R ... A NaN
.. ... .. ... .. ... .. ... .. ... .. ... ... ...
66 202046 R 149.0 R 176.0 R 85.0 R 155.0 R ... R 0.0
67 202073 R 54.0 R 60.0 R 90.0 R 54.0 R ... A NaN
68 202134 R 1752.0 R 2972.0 R 59.0 R 1943.0 R ... R 0.0
69 202152 A NaN A NaN A NaN R 63.0 R ... A NaN
70 202170 R 222.0 R 286.0 R 78.0 R 267.0 R ... R 0.0
R.12 69.1 R.13 39 R.14 57 R.15 10
0 R 122.0 R 63.0 R 52.0 R 8
1 R 51.0 R 15.0 R 29.0 R 11
2 R 1.0 R 0.0 R 0.0 R 15
3 A NaN A NaN A NaN R 13
4 A NaN A NaN A NaN R 20
.. ... ... ... ... ... ... ... ..
66 R 0.0 R 0.0 A NaN R 9
67 A NaN A NaN A NaN R 6
68 R 24.0 R 8.0 R 33.0 R 15
69 A NaN A NaN A NaN R 17
70 R 1.0 R 0.0 R 0.0 R 10
[71 rows x 33 columns],
202222 R 1975 R.1 11693 R.2 17 R.3 2006 R.4 ... R.11 0.3 \
0 202356 R 1098.0 R 3483.0 R 32.0 R 1497.0 R ... R 0.0
1 202435 R 13.0 R 34.0 R 38.0 R 1.0 R ... R 0.0
2 202453 A NaN A NaN A NaN R 20.0 R ... R 0.0
3 202480 R 2121.0 R 2300.0 R 92.0 R 2029.0 R ... R 0.0
4 202514 R 217.0 R 262.0 R 83.0 R 180.0 R ... R 0.0
.. ... .. ... .. ... .. ... .. ... .. ... ... ...
66 204486 R 901.0 R 1033.0 R 87.0 R 118.0 R ... R 0.0
67 204501 R 676.0 R 697.0 R 97.0 R 797.0 R ... A NaN
68 204608 A NaN A NaN A NaN R 550.0 Z ... A NaN
69 204617 R 202.0 R 285.0 R 71.0 R 285.0 R ... R 0.0
70 204635 R 579.0 R 664.0 R 87.0 R 608.0 R ... A NaN
R.12 2118.1 R.13 974 R.14 46 R.15 20
0 R 1232.0 R 363.0 R 29.0 R 16
1 R 14.0 R 6.0 R 43.0 R 8
2 R 6.0 R 4.0 R 67.0 R 25
3 R 6.0 R 5.0 R 83.0 R 15
4 R 1.0 R 0.0 R 0.0 R 12
.. ... ... ... ... ... ... ... ..
66 R 0.0 R 0.0 A NaN R 23
67 A NaN A NaN A NaN R 9
68 A NaN A NaN A NaN R 12
69 R 2.0 R 2.0 R 100.0 R 15
70 A NaN A NaN A NaN R 11
[71 rows x 33 columns],
204662 R 233 R.1 280 R.2 83 R.3 244 R.4 ... R.11 0.3 \
0 204671 R 321.0 R 504.0 R 64.0 R 356.0 R ... R 0.0
1 204680 R 343.0 R 493.0 R 70.0 R 421.0 R ... R 0.0
2 204699 R 367.0 R 530.0 R 69.0 R 464.0 R ... R 0.0
3 204705 R 1331.0 R 1708.0 R 78.0 R 1494.0 R ... R 0.0
4 204714 A NaN A NaN A NaN R 27.0 R ... A NaN
.. ... .. ... .. ... .. ... .. ... .. ... ... ...
66 206996 R 413.0 R 791.0 R 52.0 R 479.0 R ... R 0.0
67 207041 R 444.0 R 781.0 R 57.0 R 480.0 R ... R 0.0
68 207050 R 224.0 R 537.0 R 42.0 R 270.0 R ... R 0.0
69 207069 R 231.0 R 1191.0 R 19.0 R 222.0 R ... R 0.0
70 207087 A NaN A NaN A NaN R 2.0 R ... A NaN
R.12 3.1 R.13 2 R.14 67 R.15 15
0 R 6.0 R 3.0 R 50.0 R 20
1 R 8.0 R 4.0 R 50.0 R 18
2 R 8.0 R 2.0 R 25.0 R 18
3 R 63.0 R 20.0 R 32.0 R 29
4 A NaN A NaN A NaN R 14
.. ... ... ... ... ... ... ... ..
66 R 140.0 R 54.0 R 39.0 R 23
67 R 14.0 R 3.0 R 21.0 R 18
68 R 65.0 R 27.0 R 42.0 R 18
69 R 87.0 R 34.0 R 39.0 R 19
70 A NaN A NaN A NaN R 12
[71 rows x 33 columns],
207102 A Unnamed: 0 A.1 Unnamed: 1 A.2 Unnamed: 2 R 27 R.1 ... \
0 207157 R 32.0 R 67.0 R 48.0 R 54.0 Z ...
1 207209 R 645.0 R 719.0 R 90.0 R 346.0 R ...
2 207236 R 361.0 R 1396.0 R 26.0 R 359.0 R ...
3 207254 A NaN A NaN A NaN R 0.0 R ...
4 207263 R 661.0 R 1809.0 R 37.0 R 717.0 R ...
.. ... .. ... .. ... .. ... .. ... .. ...
66 209667 A NaN A NaN A NaN R 44.0 Z ...
67 209676 A NaN A NaN A NaN R 86.0 R ...
68 209694 A NaN A NaN A NaN R 44.0 R ...
69 209700 A NaN A NaN A NaN R 38.0 R ...
70 209719 A NaN A NaN A NaN R 49.0 R ...
A.5 Unnamed: 5 A.6 Unnamed: 6 A.7 Unnamed: 7 A.8 Unnamed: 8 R.6 16
0 Z 0.0 R 1.0 R 1.0 R 100.0 R 22
1 R 0.0 R 5.0 R 0.0 R 0.0 R 14
2 R 0.0 R 78.0 R 28.0 R 36.0 R 17
3 A NaN A NaN A NaN A NaN R 9
4 R 0.0 R 16.0 R 7.0 R 44.0 R 17
.. ... ... ... ... ... ... ... ... ... ..
66 A NaN A NaN A NaN A NaN R 8
67 A NaN A NaN A NaN A NaN R 12
68 A NaN A NaN A NaN A NaN R 7
69 A NaN A NaN A NaN A NaN R 17
70 A NaN A NaN A NaN A NaN R 19
[71 rows x 33 columns],
209746 R 1928 R.1 5899 R.2 33 R.3 2175 R.4 ... R.11 0.2 \
0 209807 R 1432.0 R 5893.0 R 24.0 R 1576.0 R ... R 0.0
1 209825 R 803.0 R 893.0 R 90.0 R 1003.0 R ... R 0.0
2 209922 R 363.0 R 399.0 R 91.0 R 394.0 R ... Z 0.0
3 209940 R 334.0 R 872.0 R 38.0 R 519.0 Z ... Z 0.0
4 210146 R 529.0 R 1545.0 R 34.0 R 622.0 Z ... Z 0.0
.. ... .. ... .. ... .. ... .. ... .. ... ... ...
66 212337 A NaN A NaN A NaN R 23.0 R ... Z 0.0
67 212355 A NaN A NaN A NaN R 67.0 R ... Z 0.0
68 212382 A NaN A NaN A NaN R 37.0 R ... Z 0.0
69 212391 A NaN A NaN A NaN R 35.0 R ... Z 0.0
70 212434 R 99.0 R 99.0 R 100.0 R 94.0 R ... A NaN
R.12 1167.1 R.13 476 R.14 41 R.15 20
0 R 98.0 R 39.0 R 40.0 R 19
1 R 0.0 R 0.0 A NaN R 11
2 R 0.0 Z 0.0 A NaN R 9
3 R 538.0 R 183.0 R 34.0 R 17
4 R 16.0 R 7.0 R 44.0 R 20
.. ... ... ... ... ... ... ... ..
66 R 17.0 R 9.0 R 53.0 R 25
67 R 8.0 R 4.0 R 50.0 R 21
68 R 14.0 R 10.0 R 71.0 R 25
69 R 7.0 R 4.0 R 57.0 R 15
70 A NaN A NaN A NaN R 7
[71 rows x 33 columns],
212577 R 553 R.1 575 R.2 96 R.3 627 R.4 ... A.2 \
0 212601 R 629.0 R 1004.0 R 63.0 R 691.0 R ... R
1 212656 R 275.0 R 378.0 R 73.0 R 310.0 R ... R
2 212674 R 640.0 R 654.0 R 98.0 R 681.0 R ... A
3 212753 A NaN A NaN A NaN R 35.0 R ... Z
4 212771 A NaN A NaN A NaN A NaN A ... A
.. ... .. ... .. ... .. ... .. ... .. ... ...
66 214944 A NaN A NaN A NaN R 130.0 R ... R
67 214971 R 19.0 R 34.0 R 56.0 R 31.0 R ... R
68 215008 A NaN A NaN A NaN R 17.0 R ... A
69 215044 A NaN A NaN A NaN A NaN A ... A
70 215053 R 72.0 R 84.0 R 86.0 R 64.0 R ... A
Unnamed: 2 A.3 Unnamed: 3 A.4 Unnamed: 4 A.5 Unnamed: 5 R.9 9
0 0.0 R 5.0 R 2.0 R 40.0 R 13
1 0.0 R 4.0 R 2.0 R 50.0 R 12
2 NaN A NaN A NaN A NaN R 10
3 0.0 R 6.0 R 2.0 R 33.0 R 32
4 NaN A NaN A NaN A NaN R 12
.. ... ... ... ... ... ... ... ... ..
66 0.0 R 46.0 R 26.0 R 57.0 R 11
67 0.0 R 1.0 R 0.0 R 0.0 R 5
68 NaN A NaN A NaN A NaN R 15
69 NaN A NaN A NaN A NaN R 15
70 NaN A NaN A NaN A NaN R 8
[71 rows x 33 columns],
215062 R 2285 R.1 2716 R.2 84 R.3 2341 R.4 ... R.11 0.2 \
0 215105 R 297.0 R 359.0 R 83.0 R 401.0 R ... Z 0.0
1 215114 R 207.0 R 273.0 R 76.0 R 177.0 R ... R 0.0
2 215132 R 316.0 R 404.0 R 78.0 R 426.0 R ... R 0.0
3 215239 R 1153.0 R 3227.0 R 36.0 R 1524.0 R ... R 0.0
4 215266 R 366.0 R 442.0 R 83.0 R 318.0 R ... A NaN
.. ... .. ... .. ... .. ... .. ... .. ... ... ...
66 217040 R 9.0 R 9.0 R 100.0 R 15.0 R ... A NaN
67 217059 R 846.0 R 1024.0 R 83.0 R 942.0 R ... R 0.0
68 217077 A NaN A NaN A NaN R 124.0 Z ... A NaN
69 217156 R 1751.0 R 1905.0 R 92.0 R 1660.0 R ... A NaN
70 217165 R 804.0 R 884.0 R 91.0 R 854.0 R ... R 0.0
R.12 48.1 R.13 45 R.14 94 R.15 6
0 R 0.0 R 0.0 A NaN R 9
1 R 0.0 R 0.0 A NaN R 11
2 R 0.0 Z 0.0 A NaN R 12
3 R 1879.0 R 708.0 R 38.0 R 18
4 A NaN A NaN A NaN R 17
.. ... ... ... ... ... ... ... ..
66 A NaN A NaN A NaN R 8
67 R 4.0 R 0.0 R 0.0 R 14
68 A NaN A NaN A NaN R 13
69 A NaN A NaN A NaN R 6
70 R 0.0 R 0.0 A NaN R 13
[71 rows x 33 columns],
217235 R 1201 R.1 1397 R.2 86 R.3 1400 R.4 ... R.11 0.3 \
0 217305 R 381.0 R 461.0 R 83.0 R 0.0 R ... A NaN
1 217323 A NaN A NaN A NaN R 408.0 R ... A NaN
2 217402 R 996.0 R 1112.0 R 90.0 R 1090.0 R ... R 0.0
3 217420 R 780.0 R 1372.0 R 57.0 R 919.0 R ... R 0.0
4 217475 R 2509.0 R 4716.0 R 53.0 R 2860.0 R ... R 0.0
.. ... .. ... .. ... .. ... .. ... .. ... ... ...
66 218894 R 1169.0 R 3718.0 R 31.0 R 1209.0 R ... Z 0.0
67 218919 R 56.0 R 78.0 R 72.0 R 163.0 R ... A NaN
68 218955 R 33.0 R 197.0 R 17.0 R 54.0 R ... Z 0.0
69 218964 R 959.0 R 1372.0 R 70.0 R 1073.0 R ... R 0.0
70 218973 R 496.0 R 518.0 R 96.0 R 474.0 R ... A NaN
R.12 13.1 R.13 3 R.14 23 R.15 16
0 A NaN A NaN A NaN R 10.0
1 A NaN A NaN A NaN R 8.0
2 R 4.0 R 2.0 R 50.0 R 11.0
3 R 34.0 R 15.0 R 44.0 R 14.0
4 R 879.0 R 327.0 R 37.0 R 20.0
.. ... ... ... ... ... ... ... ...
66 R 709.0 R 164.0 R 23.0 R 20.0
67 A NaN A NaN A NaN R 11.0
68 R 49.0 R 21.0 R 43.0 R 12.0
69 R 0.0 R 0.0 A NaN R 12.0
70 A NaN A NaN A NaN R 12.0
[71 rows x 33 columns],
218991 R 663 R.1 1633 R.2 41 R.3 804 R.4 ... Z 0.3 R.11 \
0 219000 R 318.0 R 437.0 R 73.0 R 430.0 R ... R 0.0 R
1 219037 A NaN A NaN A NaN R 19.0 R ... R 0.0 R
2 219046 R 413.0 R 1333.0 R 31.0 R 436.0 R ... R 0.0 R
3 219082 R 360.0 R 1050.0 R 34.0 R 399.0 R ... R 0.0 R
4 219091 R 176.0 R 231.0 R 76.0 R 163.0 R ... A NaN A
.. ... .. ... .. ... .. ... .. ... .. ... .. ... ...
66 220604 R 51.0 R 115.0 R 44.0 R 140.0 R ... R 0.0 R
67 220613 R 681.0 R 1525.0 R 45.0 R 787.0 R ... R 0.0 R
68 220631 R 226.0 R 577.0 R 39.0 R 231.0 R ... R 0.0 R
69 220640 A NaN A NaN A NaN R 54.0 R ... R 0.0 R
70 220701 R 185.0 R 295.0 R 63.0 R 233.0 R ... Z 0.0 R
193.1 R.12 55 R.13 28 R.14 19
0 0.0 R 0.0 A NaN R 12
1 0.0 R 0.0 A NaN R 7
2 32.0 R 15.0 R 47.0 R 16
3 21.0 R 7.0 R 33.0 R 18
4 NaN A NaN A NaN R 12
.. ... ... ... ... ... ... ..
66 5.0 R 1.0 R 20.0 R 11
67 5.0 R 0.0 R 0.0 R 15
68 3.0 R 1.0 R 33.0 R 13
69 13.0 R 9.0 R 69.0 R 25
70 0.0 Z 0.0 A NaN R 13
[71 rows x 33 columns],
220710 R 271 R.1 390 R.2 69 R.3 272 R.4 ... A.2 \
0 220756 A NaN A NaN A NaN R 41.0 R ... R
1 220765 A NaN A NaN A NaN R 42.0 R ... R
2 220853 A NaN A NaN A NaN R 155.0 R ... R
3 220862 R 2448.0 R 5476.0 R 45.0 R 2617.0 R ... R
4 220978 R 3035.0 R 5023.0 R 60.0 R 3282.0 Z ... Z
.. ... .. ... .. ... .. ... .. ... .. ... ...
66 223922 R 343.0 R 1062.0 R 32.0 R 204.0 R ... R
67 224004 R 217.0 R 397.0 R 55.0 R 233.0 R ... R
68 224013 A NaN A NaN A NaN R 8.0 R ... A
69 224110 R 425.0 R 2808.0 R 15.0 R 687.0 R ... R
70 224147 R 1448.0 R 2269.0 R 64.0 R 1744.0 R ... R
Unnamed: 2 A.3 Unnamed: 3 A.4 Unnamed: 4 A.5 Unnamed: 5 R.9 12
0 0.0 R 2.0 R 2.0 R 100.0 R 14
1 0.0 R 14.0 R 7.0 R 50.0 R 20
2 0.0 R 18.0 R 10.0 R 56.0 R 20
3 0.0 R 66.0 R 37.0 R 56.0 R 16
4 0.0 R 30.0 R 20.0 R 67.0 R 17
.. ... ... ... ... ... ... ... ... ..
66 0.0 R 470.0 R 232.0 R 49.0 R 19
67 0.0 R 2.0 R 2.0 R 100.0 R 12
68 NaN A NaN A NaN A NaN R 25
69 0.0 R 721.0 R 320.0 R 44.0 R 18
70 0.0 R 171.0 R 82.0 R 48.0 R 20
[71 rows x 33 columns],
224156 A Unnamed: 0 A.1 Unnamed: 1 A.2 Unnamed: 2 R 43 Z ... \
0 224226 R 607.0 R 866.0 R 70.0 R 571.0 R ...
1 224244 R 47.0 R 139.0 R 34.0 R 34.0 R ...
2 224271 R 88.0 R 262.0 R 34.0 R 74.0 R ...
3 224323 R 379.0 R 428.0 R 89.0 R 382.0 R ...
4 224350 R 234.0 R 1088.0 R 22.0 R 505.0 R ...
.. ... .. ... .. ... .. ... .. ... .. ...
66 227368 R 4851.0 R 6995.0 R 69.0 R 4477.0 R ...
67 227377 R 683.0 R 3428.0 R 20.0 R 801.0 Z ...
68 227386 R 286.0 R 920.0 R 31.0 R 293.0 R ...
69 227401 R 557.0 R 1832.0 R 30.0 R 637.0 R ...
70 227429 R 60.0 R 93.0 R 65.0 R 146.0 Z ...
Z.4 0.4 R.4 0.5 R.5 0.6 A.3 Unnamed: 3 R.6 18
0 R 1.0 R 1.0 R 0.0 R 0.0 R 14
1 A NaN A NaN A NaN A NaN R 9
2 A NaN A NaN A NaN A NaN R 24
3 A NaN A NaN A NaN A NaN R 12
4 R 0.0 R 651.0 R 283.0 R 43.0 R 14
.. ... ... ... ... ... ... ... ... ... ..
66 R 0.0 R 316.0 R 199.0 R 63.0 R 21
67 R 0.0 R 631.0 R 331.0 R 52.0 R 20
68 R 0.0 R 51.0 R 23.0 R 45.0 R 14
69 R 0.0 R 178.0 R 68.0 R 38.0 R 25
70 Z 0.0 R 1.0 R 1.0 R 100.0 R 18
[71 rows x 33 columns],
227526 R 1807 R.1 2344 R.2 77 R.3 1687 R.4 ... R.11 0.3 \
0 227687 R 296.0 R 908.0 R 33.0 R 260.0 Z ... Z 0.0
1 227748 A NaN A NaN A NaN R 13.0 Z ... A NaN
2 227757 R 993.0 R 1071.0 R 93.0 R 961.0 R ... A NaN
3 227845 R 594.0 R 785.0 R 76.0 R 695.0 R ... R 0.0
4 227854 R 362.0 R 1907.0 R 19.0 R 539.0 Z ... Z 0.0
.. ... .. ... .. ... .. ... .. ... .. ... ... ...
66 230047 R 585.0 R 833.0 R 70.0 R 523.0 R ... Z 0.0
67 230056 R 40.0 R 166.0 R 24.0 R 0.0 R ... R 0.0
68 230065 A NaN A NaN A NaN R 30.0 R ... R 0.0
69 230144 A NaN A NaN A NaN R 21.0 R ... R 0.0
70 230162 A NaN A NaN A NaN R 118.0 R ... R 0.0
R.12 40.1 R.13 5 R.14 13 R.15 17
0 R 401.0 R 223.0 R 56.0 R 19
1 A NaN A NaN A NaN R 9
2 A NaN A NaN A NaN R 6
3 R 2.0 R 2.0 R 100.0 R 14
4 R 765.0 R 259.0 R 34.0 R 18
.. ... ... ... ... ... ... ... ..
66 R 1.0 Z 0.0 R 0.0 R 16
67 R 0.0 R 0.0 A NaN R 14
68 R 15.0 R 11.0 R 73.0 R 12
69 R 0.0 R 0.0 A NaN R 10
70 R 322.0 R 179.0 R 56.0 R 10
[71 rows x 33 columns],
230171 R 2280 R.1 4126 R.2 55 R.3 1318 R.4 ... R.11 0.1 \
0 230199 A NaN A NaN A NaN R 35.0 R ... A NaN
1 230205 A NaN A NaN A NaN R 17.0 R ... R 0.0
2 230214 A NaN A NaN A NaN R 7.0 Z ... Z 0.0
3 230366 R 35.0 R 67.0 R 52.0 R 19.0 R ... Z 0.0
4 230418 R 307.0 R 652.0 R 47.0 R 388.0 R ... R 0.0
.. ... .. ... .. ... .. ... .. ... .. ... ... ...
66 232706 R 360.0 R 622.0 R 58.0 R 391.0 R ... R 0.0
67 232724 A NaN A NaN A NaN A NaN A ... A NaN
68 232788 R 279.0 R 485.0 R 58.0 R 304.0 R ... R 0.0
69 232797 R 38.0 R 207.0 R 18.0 R 2.0 R ... R 0.0
70 232867 R 438.0 R 773.0 R 57.0 R 515.0 R ... R 0.0
R.12 119 R.13 42 R.14 35 R.15 25
0 A NaN A NaN A NaN R 16
1 R 7.0 R 6.0 R 86.0 R 20
2 R 25.0 R 22.0 R 88.0 R 15
3 R 0.0 Z 0.0 A NaN R 19
4 R 73.0 R 34.0 R 47.0 R 16
.. ... ... ... ... ... ... ... ..
66 R 1.0 R 0.0 R 0.0 R 14
67 A NaN A NaN A NaN R 3
68 R 73.0 R 21.0 R 29.0 R 19
69 R 4.0 R 2.0 R 50.0 R 39
70 R 132.0 R 53.0 R 40.0 R 30
[71 rows x 33 columns],
232885 A Unnamed: 0 A.1 Unnamed: 1 A.2 Unnamed: 2 A.3 Unnamed: 3 A.4 \
0 232919 A NaN A NaN A NaN R 89.0 R
1 232937 R 1043.0 R 1418.0 R 74.0 R 1197.0 R
2 232946 R 4974.0 R 10148.0 R 49.0 R 5127.0 R
3 232982 R 3078.0 R 5151.0 R 60.0 R 3107.0 R
4 233019 R 333.0 R 514.0 R 65.0 R 389.0 R
.. ... .. ... .. ... .. ... .. ... ..
66 235352 A NaN A NaN A NaN R 7.0 R
67 235422 R 64.0 R 301.0 R 21.0 R 90.0 R
68 235431 R 419.0 R 1194.0 R 35.0 R 0.0 Z
69 235501 A NaN A NaN A NaN R 58.0 R
70 235547 A NaN A NaN A NaN A NaN A
... A.11 Unnamed: 11 A.12 Unnamed: 12 A.13 Unnamed: 13 A.14 \
0 ... A NaN A NaN A NaN A
1 ... R 0.0 R 0.0 R 0.0 A
2 ... R 0.0 R 3277.0 R 1752.0 R
3 ... R 0.0 R 38.0 R 26.0 R
4 ... R 0.0 R 68.0 R 28.0 R
.. ... ... ... ... ... ... ... ...
66 ... A NaN A NaN A NaN A
67 ... R 0.0 R 33.0 R 14.0 R
68 ... Z 0.0 R 0.0 R 0.0 A
69 ... A NaN A NaN A NaN A
70 ... A NaN A NaN A NaN A
Unnamed: 14 R 9
0 NaN R 12
1 NaN R 16
2 53.0 R 28
3 68.0 R 18
4 41.0 R 18
.. ... .. ..
66 NaN R 20
67 42.0 R 6
68 NaN R 15
69 NaN R 6
70 NaN R 11
[71 rows x 33 columns],
235583 A Unnamed: 0 A.1 Unnamed: 1 A.2 Unnamed: 2 R 46 Z ... \
0 235671 R 184.0 R 1025.0 R 18.0 R 163.0 Z ...
1 235699 R 163.0 R 1021.0 R 16.0 R 0.0 Z ...
2 235750 R 259.0 R 702.0 R 37.0 R 0.0 Z ...
3 236018 A NaN A NaN A NaN R 0.0 R ...
4 236072 R 300.0 R 1668.0 R 18.0 R 0.0 Z ...
.. ... .. ... .. ... .. ... .. ... .. ...
66 237899 R 273.0 R 1550.0 R 18.0 R 269.0 R ...
67 237905 A NaN A NaN A NaN A NaN A ...
68 237932 R 412.0 R 693.0 R 59.0 R 464.0 R ...
69 237950 R 279.0 R 685.0 R 41.0 R 318.0 R ...
70 237969 R 258.0 R 276.0 R 93.0 R 326.0 R ...
A.5 Unnamed: 5 A.6 Unnamed: 6 A.7 Unnamed: 7 A.8 Unnamed: 8 R.4 15
0 Z 0.0 R 16.0 R 10.0 R 63.0 R 16
1 Z 0.0 R 0.0 R 0.0 A NaN R 12
2 Z 0.0 R 0.0 R 0.0 A NaN R 14
3 A NaN A NaN A NaN A NaN R 7
4 Z 0.0 R 0.0 R 0.0 A NaN R 17
.. ... ... ... ... ... ... ... ... ... ..
66 R 0.0 R 4.0 R 1.0 R 25.0 R 12
67 A NaN A NaN A NaN A NaN R 6
68 R 0.0 R 1.0 R 0.0 R 0.0 R 11
69 R 0.0 R 3.0 R 1.0 R 33.0 R 13
70 R 0.0 R 0.0 R 0.0 A NaN R 12
[71 rows x 33 columns],
237987 R 47 R.1 103 R.2 46 R.3 49 R.4 ... A.2 \
0 237996 R 101.0 R 278.0 R 36.0 R 69 R ... A
1 238005 A NaN A NaN A NaN R 44 R ... A
2 238014 R 233.0 R 556.0 R 42.0 R 248 R ... R
3 238032 R 4479.0 R 5882.0 R 76.0 R 4940 R ... R
4 238078 R 188.0 R 290.0 R 65.0 R 75 R ... R
.. ... .. ... .. ... .. ... .. ... .. ... ...
66 240693 R 355.0 R 1123.0 R 32.0 R 387 R ... R
67 240709 A NaN A NaN A NaN R 26 R ... R
68 240718 A NaN A NaN A NaN R 251 R ... A
69 240727 R 1401.0 R 2363.0 R 59.0 R 1752 R ... R
70 240736 R 281.0 R 374.0 R 75.0 R 0 R ... R
Unnamed: 2 A.3 Unnamed: 3 A.4 Unnamed: 4 A.5 Unnamed: 5 R.9 22
0 NaN A NaN A NaN A NaN R 26
1 NaN A NaN A NaN A NaN R 20
2 0.0 R 36.0 R 12.0 R 33.0 R 11
3 0.0 R 9.0 R 1.0 R 11.0 R 21
4 0.0 R 46.0 R 29.0 R 63.0 R 12
.. ... ... ... ... ... ... ... ... ..
66 0.0 R 52.0 R 13.0 R 25.0 R 11
67 0.0 R 18.0 R 11.0 R 61.0 R 10
68 NaN A NaN A NaN A NaN R 15
69 0.0 R 8.0 R 0.0 R 0.0 R 14
70 0.0 R 0.0 R 0.0 A NaN R 14
[71 rows x 33 columns],
240745 R 339 R.1 779 R.2 44 R.3 0 R.4 ... R.10 0.7 \
0 240754 R 409.0 R 552.0 R 74.0 R 384.0 R ... R 0.0
1 240790 R 252.0 R 302.0 R 83.0 R 60.0 R ... R 0.0
2 240879 A NaN A NaN A NaN R 155.0 R ... A NaN
3 240985 A NaN A NaN A NaN R 22.0 R ... A NaN
4 241100 R 37.0 R 49.0 R 76.0 R 28.0 R ... R 0.0
.. ... .. ... .. ... .. ... .. ... .. ... ... ...
66 243647 R 123.0 R 176.0 R 70.0 R 111.0 R ... R 0.0
67 243665 R 259.0 R 381.0 R 68.0 R 322.0 R ... R 0.0
68 243744 R 1606.0 R 1673.0 R 96.0 R 1698.0 R ... Z 0.0
69 243780 R 8887.0 R 10114.0 R 88.0 R 8132.0 R ... Z 0.0
70 243799 A NaN A NaN A NaN R 0.0 R ... A NaN
R.11 0.8 R.12 0.9 A.1 Unnamed: 1 R.13 15
0 R 32.0 R 17.0 R 53.0 R 17
1 R 4.0 R 1.0 R 25.0 R 24
2 A NaN A NaN A NaN R 29
3 A NaN A NaN A NaN R 20
4 R 1.0 R 0.0 R 0.0 R 17
.. ... ... ... ... ... ... ... ..
66 R 15.0 R 11.0 R 73.0 R 10
67 R 40.0 R 13.0 R 33.0 R 12
68 R 0.0 R 0.0 A NaN R 4
69 R 30.0 R 21.0 R 70.0 R 13
70 A NaN A NaN A NaN R 8
[71 rows x 33 columns],
243823 R 35 R.1 142 R.2 25 R.3 36 R.4 ... Z.1 0.3 \
0 243832 R 94.0 R 418.0 R 22.0 R 26.0 R ... R 0.0
1 243841 R 57.0 R 152.0 R 38.0 R 254.0 R ... R 0.0
2 244233 R 14.0 R 121.0 R 12.0 R 0.0 R ... R 0.0
3 244279 A NaN A NaN A NaN R 25.0 R ... A NaN
4 244437 R 2296.0 R 6143.0 R 37.0 R 2965.0 R ... R 0.0
.. ... .. ... .. ... .. ... .. ... .. ... ... ...
66 260813 R 7.0 R 26.0 R 27.0 R 1.0 Z ... A NaN
67 260929 A NaN A NaN A NaN R 1.0 Z ... Z 0.0
68 260965 A NaN A NaN A NaN R 9.0 Z ... A NaN
69 260992 R 37.0 R 108.0 R 34.0 R 0.0 R ... R 0.0
70 261436 A NaN A NaN A NaN R 289.0 Z ... A NaN
R.10 5.1 R.11 3 R.12 60 R.13 10
0 R 2.0 R 1.0 R 50.0 R 20
1 R 7.0 R 3.0 R 43.0 R 17
2 R 0.0 R 0.0 A NaN R 9
3 A NaN A NaN A NaN R 18
4 R 967.0 R 509.0 R 53.0 R 20
.. ... ... ... ... ... ... ... ..
66 A NaN A NaN A NaN R 11
67 R 0.0 R 0.0 A NaN R 15
68 A NaN A NaN A NaN R 8
69 R 0.0 R 0.0 A NaN R 14
70 A NaN A NaN A NaN R 14
[71 rows x 33 columns],
261676 A Unnamed: 0 A.1 Unnamed: 1 A.2 Unnamed: 2 R 25 R.1 ... \
0 261685 A NaN A NaN A NaN R 21.0 R ...
1 261719 A NaN A NaN A NaN R 43.0 R ...
2 261773 A NaN A NaN A NaN R 4.0 Z ...
3 261861 R 32.0 R 52.0 R 62.0 R 29.0 R ...
4 262031 R 991.0 R 1808.0 R 55.0 R 978.0 R ...
.. ... .. ... .. ... .. ... .. ... .. ...
66 366632 A NaN A NaN A NaN R 17.0 R ...
67 366711 R 2117.0 R 4666.0 R 45.0 R 2131.0 Z ...
68 367051 A NaN A NaN A NaN R 22.0 R ...
69 367088 A NaN A NaN A NaN R 9.0 R ...
70 367103 A NaN A NaN A NaN R 19.0 R ...
A.5 Unnamed: 5 A.6 Unnamed: 6 A.7 Unnamed: 7 A.8 Unnamed: 8 R.6 9
0 A NaN A NaN A NaN A NaN R 8
1 A NaN A NaN A NaN A NaN R 18
2 R 0.0 R 1.0 R 0.0 R 0.0 R 3
3 A NaN A NaN A NaN A NaN R 15
4 R 0.0 R 312.0 R 124.0 R 40.0 R 20
.. ... ... ... ... ... ... ... ... ... ..
66 A NaN A NaN A NaN A NaN R 8
67 Z 0.0 R 114.0 R 64.0 R 56.0 R 27
68 R 0.0 R 25.0 R 23.0 R 92.0 R 15
69 R 0.0 R 5.0 R 2.0 R 40.0 R 29
70 A NaN A NaN A NaN A NaN R 12
[71 rows x 33 columns],
367112 A Unnamed: 0 A.1 Unnamed: 1 A.2 Unnamed: 2 R 70 R.1 ... \
0 367158 A NaN A NaN A NaN R 38.0 R ...
1 367334 A NaN A NaN A NaN A NaN A ...
2 367361 A NaN A NaN A NaN R 10.0 R ...
3 367431 A NaN A NaN A NaN R 11.0 R ...
4 367459 R 759.0 R 3869.0 R 20.0 R 1033.0 R ...
.. ... .. ... .. ... .. ... .. ... .. ...
66 375656 A NaN A NaN A NaN R 30.0 R ...
67 375683 A NaN A NaN A NaN R 67.0 Z ...
68 375726 A NaN A NaN A NaN R 110.0 R ...
69 375939 A NaN A NaN A NaN R 10.0 Z ...
70 375966 A NaN A NaN A NaN R 2.0 R ...
R.8 0.3 R.9 2.1 R.10 0.4 R.11 0.5 R.12 43
0 A NaN A NaN A NaN A NaN R 30
1 A NaN A NaN A NaN A NaN R 10
2 A NaN A NaN A NaN A NaN R 12
3 A NaN A NaN A NaN A NaN R 10
4 R 0.0 R 735.0 R 260.0 R 35.0 R 16
.. ... ... ... ... ... ... ... ... ... ..
66 R 0.0 R 17.0 R 13.0 R 76.0 R 5
67 Z 0.0 R 34.0 R 31.0 R 91.0 R 16
68 R 0.0 R 56.0 R 21.0 R 38.0 R 4
69 A NaN A NaN A NaN A NaN R 10
70 R 0.0 R 0.0 R 0.0 A NaN R 8
[71 rows x 33 columns],
375984 A Unnamed: 0 A.1 Unnamed: 1 A.2 Unnamed: 2 R 95 R.1 ... \
0 376224 R 32.0 R 48.0 R 67.0 R 11.0 R ...
1 376242 A NaN A NaN A NaN R 57.0 R ...
2 376288 A NaN A NaN A NaN R 32.0 R ...
3 376321 R 129.0 R 409.0 R 32.0 R 10.0 R ...
4 376330 A NaN A NaN A NaN R 23.0 R ...
.. ... .. ... .. ... .. ... .. ... .. ...
66 383765 A NaN A NaN A NaN R 60.0 R ...
67 383996 R 39.0 R 211.0 R 18.0 R 54.0 R ...
68 384236 A NaN A NaN A NaN R 103.0 R ...
69 384245 A NaN A NaN A NaN R 90.0 R ...
70 384254 R 81.0 R 103.0 R 79.0 R 98.0 R ...
Z.1 0.3 R.7 25.1 R.8 10 R.9 40 R.10 24
0 A NaN A NaN A NaN A NaN R 18
1 A NaN A NaN A NaN A NaN R 25
2 A NaN A NaN A NaN A NaN R 45
3 R 0.0 R 5.0 R 1.0 R 20.0 R 10
4 A NaN A NaN A NaN A NaN R 19
.. ... ... ... ... ... ... ... ... ... ..
66 Z 0.0 R 21.0 R 15.0 R 71.0 R 25
67 R 0.0 R 20.0 R 8.0 R 40.0 R 15
68 A NaN A NaN A NaN A NaN R 25
69 A NaN A NaN A NaN A NaN R 25
70 R 0.0 R 0.0 R 0.0 A NaN R 11
[71 rows x 33 columns],
384333 R 582 R.1 1766 R.2 33 R.3 813 R.4 ... Z.1 0.3 \
0 384342 R 519.0 R 2007.0 R 26.0 R 557.0 R ... R 0.0
1 384412 R 14.0 R 20.0 R 70.0 R 5.0 R ... A NaN
2 384421 R 20.0 R 23.0 R 87.0 R 23.0 R ... A NaN
3 385132 A NaN A NaN A NaN R 18.0 R ... R 0.0
4 385503 A NaN A NaN A NaN R 57.0 Z ... A NaN
.. ... .. ... .. ... .. ... .. ... .. ... ... ...
66 407179 A NaN A NaN A NaN R 17.0 R ... Z 0.0
67 407355 A NaN A NaN A NaN R 14.0 R ... A NaN
68 407391 A NaN A NaN A NaN R 24.0 R ... R 0.0
69 407407 A NaN A NaN A NaN R 2.0 R ... R 0.0
70 407425 A NaN A NaN A NaN R 6.0 Z ... Z 0.0
R.10 544.1 R.11 228 R.12 42 R.13 19
0 R 184.0 R 82.0 R 45.0 R 18.0
1 A NaN A NaN A NaN R 14.0
2 A NaN A NaN A NaN R 15.0
3 R 5.0 R 3.0 R 60.0 R 14.0
4 A NaN A NaN A NaN R 21.0
.. ... ... ... ... ... ... ... ...
66 R 6.0 R 5.0 R 83.0 R 9.0
67 A NaN A NaN A NaN R 11.0
68 R 18.0 R 18.0 R 100.0 R 9.0
69 R 22.0 R 22.0 R 100.0 R 13.0
70 R 2.0 R 2.0 R 100.0 R 14.0
[71 rows x 33 columns],
407434 A Unnamed: 0 A.1 Unnamed: 1 A.2 Unnamed: 2 R 16 R.1 ... \
0 407461 A NaN A NaN A NaN R 39.0 R ...
1 407470 A NaN A NaN A NaN R 74.0 R ...
2 407489 A NaN A NaN A NaN R 35.0 R ...
3 407513 A NaN A NaN A NaN R 30.0 R ...
4 407522 A NaN A NaN A NaN A NaN A ...
.. ... .. ... .. ... .. ... .. ... .. ...
66 417275 A NaN A NaN A NaN R 24.0 R ...
67 417327 R 12.0 R 46.0 R 26.0 R 7.0 R ...
68 417442 A NaN A NaN A NaN R 17.0 R ...
69 417503 A NaN A NaN A NaN R 8.0 R ...
70 417600 A NaN A NaN A NaN R 10.0 R ...
R.8 0.3 R.9 13.1 R.10 10 R.11 77 R.12 10.1
0 A NaN A NaN A NaN A NaN R 4
1 Z 0.0 R 25.0 R 9.0 R 36.0 R 19
2 R 0.0 R 25.0 R 24.0 R 96.0 R 10
3 R 0.0 R 15.0 R 12.0 R 80.0 R 11
4 A NaN A NaN A NaN A NaN R 7
.. ... ... ... ... ... ... ... ... ... ...
66 A NaN A NaN A NaN A NaN R 18
67 R 0.0 R 4.0 R 2.0 R 50.0 R 10
68 A NaN A NaN A NaN A NaN R 14
69 R 0.0 R 2.0 R 0.0 R 0.0 R 5
70 A NaN A NaN A NaN A NaN R 7
[71 rows x 33 columns],
417628 A Unnamed: 0 A.1 Unnamed: 1 A.2 Unnamed: 2 R 7 R.1 ... \
0 417637 A NaN A NaN A NaN R 25.0 R ...
1 417646 A NaN A NaN A NaN R 10.0 Z ...
2 417655 A NaN A NaN A NaN R 21.0 R ...
3 417682 A NaN A NaN A NaN R 1.0 R ...
4 417716 A NaN A NaN A NaN R 8.0 R ...
.. ... .. ... .. ... .. ... .. ... .. ...
66 419484 A NaN A NaN A NaN R 11.0 R ...
67 419633 A NaN A NaN A NaN R 27.0 R ...
68 419703 A NaN A NaN A NaN R 315.0 Z ...
69 419712 A NaN A NaN A NaN R 98.0 Z ...
70 419721 A NaN A NaN A NaN R 147.0 Z ...
R.8 0.3 R.9 4.1 R.10 4.2 R.11 100 R.12 3
0 A NaN A NaN A NaN A NaN R 7
1 A NaN A NaN A NaN A NaN R 8
2 A NaN A NaN A NaN A NaN R 5
3 A NaN A NaN A NaN A NaN R 10
4 A NaN A NaN A NaN A NaN R 13
.. ... .. ... .. ... .. ... .. ... ..
66 A NaN A NaN A NaN A NaN R 14
67 A NaN A NaN A NaN A NaN R 10
68 A NaN A NaN A NaN A NaN R 26
69 A NaN A NaN A NaN A NaN R 13
70 A NaN A NaN A NaN A NaN R 10
[71 rows x 33 columns],
420024 R 20 R.1 20.1 R.2 100 R.3 0 Z ... A.3 Unnamed: 3 \
0 420042 A NaN A NaN A NaN R 2.0 R ... A NaN
1 420130 A NaN A NaN A NaN R 58.0 Z ... A NaN
2 420255 A NaN A NaN A NaN R 19.0 R ... A NaN
3 420325 R 25.0 R 31.0 R 81.0 R 24.0 R ... A NaN
4 420343 A NaN A NaN A NaN R 222.0 R ... R 0.0
.. ... .. ... .. ... .. ... .. ... .. ... ... ...
66 431071 A NaN A NaN A NaN R 8.0 R ... R 0.0
67 431099 A NaN A NaN A NaN R 30.0 R ... R 0.0
68 431105 A NaN A NaN A NaN R 6.0 R ... Z 0.0
69 431123 A NaN A NaN A NaN R 81.0 R ... A NaN
70 431141 A NaN A NaN A NaN R 223.0 R ... A NaN
A.4 Unnamed: 4 A.5 Unnamed: 5 A.6 Unnamed: 6 R.5 14
0 A NaN A NaN A NaN R 8
1 A NaN A NaN A NaN R 30
2 A NaN A NaN A NaN R 14
3 A NaN A NaN A NaN R 14
4 R 43.0 R 35.0 R 81.0 R 26
.. ... ... ... ... ... ... ... ..
66 R 2.0 R 1.0 R 50.0 R 12
67 R 22.0 R 13.0 R 59.0 R 9
68 R 19.0 R 10.0 R 53.0 R 6
69 A NaN A NaN A NaN R 14
70 A NaN A NaN A NaN R 13
[71 rows x 33 columns],
431169 A Unnamed: 0 A.1 Unnamed: 1 A.2 Unnamed: 2 R 16 R.1 ... \
0 431187 A NaN A NaN A NaN R 77.0 R ...
1 431196 A NaN A NaN A NaN R 10.0 R ...
2 431266 A NaN A NaN A NaN A NaN A ...
3 431275 A NaN A NaN A NaN R 3.0 R ...
4 431284 A NaN A NaN A NaN R 4.0 R ...
.. ... .. ... .. ... .. ... .. ... .. ...
66 437316 A NaN A NaN A NaN A NaN A ...
67 437325 A NaN A NaN A NaN A NaN A ...
68 437556 A NaN A NaN A NaN R 414.0 R ...
69 437608 A NaN A NaN A NaN R 42.0 R ...
70 437635 A NaN A NaN A NaN R 137.0 Z ...
R.8 0.4 R.9 0.5 R.10 0.6 A.3 Unnamed: 3 R.11 7
0 A NaN A NaN A NaN A NaN R 7
1 A NaN A NaN A NaN A NaN R 24
2 R 0.0 R 44.0 R 24.0 R 55.0 R 10
3 R 0.0 R 6.0 R 4.0 R 67.0 R 7
4 R 0.0 R 3.0 R 2.0 R 67.0 R 25
.. ... ... ... ... ... ... ... ... ... ..
66 A NaN A NaN A NaN A NaN R 14
67 A NaN A NaN A NaN A NaN R 6
68 R 0.0 R 14.0 R 14.0 R 100.0 R 18
69 R 0.0 R 9.0 R 7.0 R 78.0 R 20
70 A NaN A NaN A NaN A NaN R 19
[71 rows x 33 columns],
437705 A Unnamed: 0 A.1 Unnamed: 1 A.2 Unnamed: 2 R 8 R.1 ... \
0 437723 A NaN A NaN A NaN R 78.0 R ...
1 437732 A NaN A NaN A NaN R 0.0 R ...
2 437750 R 40.0 R 40.0 R 100.0 R 46.0 R ...
3 437769 A NaN A NaN A NaN R 30.0 R ...
4 437778 A NaN A NaN A NaN R 197.0 R ...
.. ... .. ... .. ... .. ... .. ... .. ...
66 441168 A NaN A NaN A NaN R 13.0 Z ...
67 441210 A NaN A NaN A NaN R 0.0 R ...
68 441229 R 180.0 R 268.0 R 67.0 R 157.0 R ...
69 441256 A NaN A NaN A NaN R 13.0 R ...
70 441371 A NaN A NaN A NaN R 4693.0 R ...
R.8 0.4 R.9 0.5 R.10 0.6 A.3 Unnamed: 3 R.11 3
0 A NaN A NaN A NaN A NaN R 15
1 A NaN A NaN A NaN A NaN R 8
2 A NaN A NaN A NaN A NaN R 17
3 A NaN A NaN A NaN A NaN R 20
4 A NaN A NaN A NaN A NaN R 25
.. ... ... ... ... ... ... ... ... ... ..
66 A NaN A NaN A NaN A NaN R 10
67 R 0.0 R 61.0 R 11.0 R 18.0 R 15
68 A NaN A NaN A NaN A NaN R 7
69 A NaN A NaN A NaN A NaN R 4
70 A NaN A NaN A NaN A NaN R 16
[71 rows x 33 columns],
441380 A Unnamed: 0 A.1 Unnamed: 1 A.2 Unnamed: 2 R 21 R.1 ... \
0 441414 A NaN A NaN A NaN R 17.0 R ...
1 441423 A NaN A NaN A NaN R 206.0 R ...
2 441487 R 7.0 R 35.0 R 20.0 R 8.0 R ...
3 441496 A NaN A NaN A NaN R 29.0 Z ...
4 441502 A NaN A NaN A NaN R 101.0 R ...
.. ... .. ... .. ... .. ... .. ... .. ...
66 443340 R 4.0 R 9.0 R 44.0 R 5.0 R ...
67 443377 R 13.0 R 16.0 R 81.0 R 11.0 R ...
68 443410 R 159.0 R 286.0 R 56.0 R 185.0 R ...
69 443492 R 308.0 R 507.0 R 61.0 R 325.0 R ...
70 443562 R 38.0 R 70.0 R 54.0 R 54.0 R ...
R.8 0.3 R.9 11.1 R.10 0.4 R.11 0.5 R.12 25
0 R 0.0 R 69.0 R 54.0 R 78.0 R 20
1 A NaN A NaN A NaN A NaN R 22
2 R 0.0 R 1.0 R 0.0 R 0.0 R 10
3 A NaN A NaN A NaN A NaN R 10
4 A NaN A NaN A NaN A NaN R 18
.. ... ... ... ... ... ... ... ... ... ..
66 R 0.0 R 1.0 R 1.0 R 100.0 R 7
67 A NaN A NaN A NaN A NaN R 6
68 R 0.0 R 1.0 R 1.0 R 100.0 R 10
69 Z 0.0 R 40.0 R 17.0 R 43.0 R 14
70 R 0.0 R 16.0 R 10.0 R 63.0 R 15
[71 rows x 33 columns],
443571 A Unnamed: 0 A.1 Unnamed: 1 A.2 Unnamed: 2 R 55 R.1 ... \
0 443599 R 3.0 R 233.0 R 1.0 R 1.0 R ...
1 443632 A NaN A NaN A NaN R 23.0 Z ...
2 443641 A NaN A NaN A NaN R 9.0 Z ...
3 443650 A NaN A NaN A NaN R 116.0 R ...
4 443669 A NaN A NaN A NaN A NaN A ...
.. ... .. ... .. ... .. ... .. ... .. ...
66 445498 A NaN A NaN A NaN R 25.0 R ...
67 445540 A NaN A NaN A NaN R 18.0 R ...
68 445638 A NaN A NaN A NaN A NaN A ...
69 445647 A NaN A NaN A NaN A NaN A ...
70 445656 A NaN A NaN A NaN A NaN A ...
A.5 Unnamed: 5 A.6 Unnamed: 6 A.7 Unnamed: 7 A.8 Unnamed: 8 R.5 15
0 R 0.0 R 1.0 R 0.0 R 0.0 R 19
1 A NaN A NaN A NaN A NaN R 13
2 Z 0.0 R 9.0 R 8.0 R 89.0 R 15
3 R 0.0 R 3.0 R 2.0 R 67.0 R 31
4 A NaN A NaN A NaN A NaN R 8
.. ... ... ... ... ... ... ... ... ... ..
66 A NaN A NaN A NaN A NaN R 11
67 A NaN A NaN A NaN A NaN R 19
68 A NaN A NaN A NaN A NaN R 19
69 A NaN A NaN A NaN A NaN R 14
70 A NaN A NaN A NaN A NaN R 18
[71 rows x 33 columns],
445692 R 205 R.1 227 R.2 90 R.3 183 R.4 ... R.11 0.4 \
0 445708 R 473.0 R 519.0 R 91.0 R 330.0 R ... R 0.0
1 445735 A NaN A NaN A NaN A NaN A ... A NaN
2 445744 A NaN A NaN A NaN R 42.0 Z ... A NaN
3 445762 A NaN A NaN A NaN R 13.0 R ... A NaN
4 445780 A NaN A NaN A NaN R 2.0 Z ... Z 0.0
.. ... .. ... .. ... .. ... .. ... .. ... ... ...
66 447795 A NaN A NaN A NaN R 32.0 R ... A NaN
67 447810 A NaN A NaN A NaN R 110.0 R ... A NaN
68 447847 R 30.0 R 39.0 R 77.0 R 73.0 Z ... A NaN
69 447865 A NaN A NaN A NaN R 13.0 R ... R 0.0
70 447874 A NaN A NaN A NaN R 27.0 R ... A NaN
R.12 0.5 R.13 0.6 A Unnamed: 0 R.14 30
0 R 0.0 R 0.0 A NaN R 15
1 A NaN A NaN A NaN R 10
2 A NaN A NaN A NaN R 24
3 A NaN A NaN A NaN R 11
4 R 1.0 R 1.0 R 100.0 R 4
.. ... ... ... ... .. ... ... ..
66 A NaN A NaN A NaN R 10
67 A NaN A NaN A NaN R 10
68 A NaN A NaN A NaN R 5
69 R 9.0 R 7.0 R 78.0 R 10
70 A NaN A NaN A NaN R 14
[71 rows x 33 columns],
447883 A Unnamed: 0 A.1 Unnamed: 1 A.2 Unnamed: 2 R 44 R.1 ... \
0 447892 A NaN A NaN A NaN R 32.0 R ...
1 447908 A NaN A NaN A NaN R 4.0 Z ...
2 447917 A NaN A NaN A NaN A NaN A ...
3 447935 R 47.0 R 96.0 R 49.0 R 63.0 R ...
4 447953 R 34.0 R 108.0 R 31.0 R 70.0 R ...
.. ... .. ... .. ... .. ... .. ... .. ...
66 449773 A NaN A NaN A NaN A NaN A ...
67 449782 A NaN A NaN A NaN R 16.0 R ...
68 449807 A NaN A NaN A NaN R 27.0 R ...
69 449816 A NaN A NaN A NaN R 29.0 R ...
70 449861 A NaN A NaN A NaN R 96.0 R ...
R.8 0.3 R.9 47.1 R.10 25 R.11 53 R.12 7
0 Z 0.0 R 9.0 R 5.0 R 56.0 R 17
1 Z 0.0 R 1.0 R 1.0 R 100.0 R 20
2 A NaN A NaN A NaN A NaN R 11
3 A NaN A NaN A NaN A NaN R 15
4 R 0.0 R 4.0 R 2.0 R 50.0 R 10
.. ... ... ... ... ... ... ... ... ... ..
66 A NaN A NaN A NaN A NaN R 12
67 R 0.0 R 24.0 R 17.0 R 71.0 R 12
68 A NaN A NaN A NaN A NaN R 21
69 R 0.0 R 59.0 R 39.0 R 66.0 R 8
70 A NaN A NaN A NaN A NaN R 19
[71 rows x 33 columns],
449870 R 7 R.1 22 R.2 32 R.3 8 R.4 ... A.2 Unnamed: 2 \
0 449889 A NaN A NaN A NaN A NaN A ... A NaN
1 449898 R 12.0 R 98.0 R 12.0 R 6.0 R ... R 0.0
2 449904 A NaN A NaN A NaN R 113.0 R ... A NaN
3 449931 R 1.0 R 44.0 R 2.0 R 4.0 R ... R 0.0
4 449959 A NaN A NaN A NaN R 30.0 Z ... Z 0.0
.. ... .. ... .. ... .. ... .. ... .. ... ... ...
66 451574 A NaN A NaN A NaN R 35.0 R ... A NaN
67 451583 A NaN A NaN A NaN R 52.0 R ... R 0.0
68 451626 A NaN A NaN A NaN R 46.0 R ... R 0.0
69 451714 A NaN A NaN A NaN R 42.0 Z ... Z 0.0
70 451741 R 40.0 R 62.0 R 65.0 R 0.0 R ... A NaN
A.3 Unnamed: 3 A.4 Unnamed: 4 A.5 Unnamed: 5 R.9 5
0 A NaN A NaN A NaN R 10
1 R 1.0 R 0.0 R 0.0 R 13
2 A NaN A NaN A NaN R 17
3 R 5.0 R 2.0 R 40.0 R 9
4 R 20.0 R 18.0 R 90.0 R 15
.. ... ... ... ... ... ... ... ..
66 A NaN A NaN A NaN R 10
67 R 105.0 R 75.0 R 71.0 R 8
68 R 5.0 R 0.0 R 0.0 R 7
69 R 0.0 R 0.0 A NaN R 18
70 A NaN A NaN A NaN R 15
[71 rows x 33 columns],
451750 R 170 R.1 539 R.2 32 R.3 39 R.4 ... R.11 0.4 R.12 \
0 451820 R 26.0 R 52.0 R 50.0 R 30.0 Z ... R 0.0 R
1 451857 A NaN A NaN A NaN R 57.0 R ... A NaN A
2 451866 A NaN A NaN A NaN R 0.0 R ... A NaN A
3 451918 A NaN A NaN A NaN R 15.0 R ... A NaN A
4 451927 R 76.0 R 113.0 R 67.0 R 65.0 R ... R 0.0 R
.. ... .. ... .. ... .. ... .. ... .. ... ... ... ...
66 455196 A NaN A NaN A NaN R 94.0 Z ... A NaN A
67 455202 A NaN A NaN A NaN R 54.0 Z ... Z 0.0 R
68 455211 A NaN A NaN A NaN R 61.0 R ... A NaN A
69 455220 A NaN A NaN A NaN R 45.0 R ... A NaN A
70 455239 A NaN A NaN A NaN R 8.0 R ... R 0.0 R
0.5 R.13 0.6 A Unnamed: 0 R.14 18
0 14.0 R 4.0 R 29.0 R 23
1 NaN A NaN A NaN R 7
2 NaN A NaN A NaN R 11
3 NaN A NaN A NaN R 12
4 11.0 R 8.0 R 73.0 R 12
.. ... ... ... .. ... ... ..
66 NaN A NaN A NaN R 26
67 2.0 R 1.0 R 50.0 R 15
68 NaN A NaN A NaN R 9
69 NaN A NaN A NaN R 12
70 3.0 R 3.0 R 100.0 R 8
[71 rows x 33 columns],
455257 R 60 R.1 76 R.2 79 R.3 90 R.4 ... A.2 Unnamed: 2 \
0 455275 A NaN A NaN A NaN R 80.0 R ... A NaN
1 455284 A NaN A NaN A NaN R 33.0 Z ... Z 0.0
2 455327 A NaN A NaN A NaN A NaN A ... A NaN
3 455336 A NaN A NaN A NaN R 70.0 R ... A NaN
4 455354 A NaN A NaN A NaN R 55.0 R ... A NaN
.. ... .. ... .. ... .. ... .. ... .. ... ... ...
66 457192 A NaN A NaN A NaN R 11.0 R ... A NaN
67 457208 A NaN A NaN A NaN R 23.0 R ... A NaN
68 457226 R 4.0 R 11.0 R 36.0 R 0.0 R ... R 0.0
69 457253 A NaN A NaN A NaN R 5.0 R ... R 0.0
70 457299 A NaN A NaN A NaN R 0.0 R ... R 0.0
A.3 Unnamed: 3 A.4 Unnamed: 4 A.5 Unnamed: 5 R.9 27
0 A NaN A NaN A NaN R 15
1 R 14.0 R 12.0 R 86.0 R 14
2 A NaN A NaN A NaN R 7
3 A NaN A NaN A NaN R 20
4 A NaN A NaN A NaN R 15
.. ... ... ... ... ... ... ... ..
66 A NaN A NaN A NaN R 10
67 A NaN A NaN A NaN R 15
68 R 2.0 R 1.0 R 50.0 R 5
69 R 9.0 R 7.0 R 78.0 R 15
70 R 0.0 R 0.0 A NaN R 25
[71 rows x 33 columns],
457314 A Unnamed: 0 A.1 Unnamed: 1 A.2 Unnamed: 2 R 54 R.1 ... \
0 457323 A NaN A NaN A NaN R 72.0 R ...
1 457332 A NaN A NaN A NaN R 8.0 R ...
2 457341 A NaN A NaN A NaN R 20.0 R ...
3 457350 A NaN A NaN A NaN A NaN A ...
4 457378 A NaN A NaN A NaN R 37.0 R ...
.. ... .. ... .. ... .. ... .. ... .. ...
66 458274 A NaN A NaN A NaN R 18.0 Z ...
67 458380 A NaN A NaN A NaN R 26.0 R ...
68 458405 A NaN A NaN A NaN R 94.0 R ...
69 458441 A NaN A NaN A NaN R 79.0 R ...
70 458496 R 17.0 R 58.0 R 29.0 R 15.0 R ...
A.5 Unnamed: 5 A.6 Unnamed: 6 A.7 Unnamed: 7 A.8 Unnamed: 8 R.6 10
0 A NaN A NaN A NaN A NaN R 22
1 R 0.0 R 0.0 R 0.0 A NaN R 9
2 R 0.0 R 0.0 R 0.0 A NaN R 13
3 A NaN A NaN A NaN A NaN P 15
4 R 0.0 R 50.0 R 27.0 R 54.0 R 14
.. ... ... ... ... ... ... ... ... ... ..
66 Z 0.0 R 0.0 R 0.0 A NaN R 15
67 A NaN A NaN A NaN A NaN R 19
68 A NaN A NaN A NaN A NaN R 20
69 R 0.0 R 1.0 R 1.0 R 100.0 R 27
70 R 0.0 R 8.0 R 4.0 R 50.0 R 20
[71 rows x 33 columns],
458681 A Unnamed: 0 A.1 Unnamed: 1 A.2 Unnamed: 2 R 47 Z ... \
0 458803 A NaN A NaN A NaN R 36.0 R ...
1 458812 A NaN A NaN A NaN R 16.0 R ...
2 458821 A NaN A NaN A NaN R 17.0 R ...
3 458830 A NaN A NaN A NaN R 45.0 R ...
4 458858 A NaN A NaN A NaN R 34.0 R ...
.. ... .. ... .. ... .. ... .. ... .. ...
66 460190 A NaN A NaN A NaN R 61.0 Z ...
67 460206 A NaN A NaN A NaN R 156.0 Z ...
68 460349 R 6.0 R 317.0 R 2.0 R 2.0 R ...
69 460376 A NaN A NaN A NaN R 4.0 R ...
70 460385 A NaN A NaN A NaN R 32.0 R ...
A.5 Unnamed: 5 A.6 Unnamed: 6 A.7 Unnamed: 7 A.8 Unnamed: 8 R.4 35
0 Z 0.0 R 9.0 R 6.0 R 67.0 R 13
1 Z 0.0 R 0.0 R 0.0 A NaN R 18
2 A NaN A NaN A NaN A NaN R 14
3 Z 0.0 R 5.0 R 2.0 R 40.0 R 21
4 Z 0.0 R 22.0 R 8.0 R 36.0 R 24
.. ... ... ... ... ... ... ... ... ... ..
66 A NaN A NaN A NaN A NaN R 28
67 A NaN A NaN A NaN A NaN R 29
68 R 0.0 R 16.0 R 5.0 R 31.0 R 11
69 R 0.0 R 0.0 R 0.0 A NaN R 4
70 A NaN A NaN A NaN A NaN R 11
[71 rows x 33 columns],
460394 R 514 R.1 3013 R.2 17 R.3 846 R.4 ... R.11 0.3 \
0 460455 A NaN A NaN A NaN R 2.0 R ... R 0.0
1 460464 R 593.0 R 3372.0 R 18.0 R 776.0 R ... R 0.0
2 460482 A NaN A NaN A NaN R 35.0 R ... A NaN
3 460516 A NaN A NaN A NaN R 124.0 R ... A NaN
4 460525 A NaN A NaN A NaN A NaN A ... A NaN
.. ... .. ... .. ... .. ... .. ... .. ... ... ...
66 461722 A NaN A NaN A NaN R 5.0 R ... A NaN
67 461740 A NaN A NaN A NaN R 13.0 R ... A NaN
68 461759 R 14.0 R 22.0 R 64.0 R 24.0 R ... R 0.0
69 461768 A NaN A NaN A NaN A NaN A ... A NaN
70 461786 A NaN A NaN A NaN R 24.0 R ... A NaN
R.12 960.1 R.13 347 R.14 36 R.15 21
0 R 24.0 R 16.0 R 67.0 R 4
1 R 900.0 R 347.0 R 39.0 R 29
2 A NaN A NaN A NaN R 10
3 A NaN A NaN A NaN R 14
4 A NaN A NaN A NaN R 11
.. ... ... ... ... ... ... ... ..
66 A NaN A NaN A NaN R 7
67 A NaN A NaN A NaN R 23
68 R 0.0 R 0.0 A NaN R 4
69 A NaN A NaN A NaN R 41
70 A NaN A NaN A NaN R 5
[71 rows x 33 columns],
461795 R 124 R.1 189 R.2 66 R.3 49 R.4 ... R.11 0.3 R.12 \
0 461810 A NaN A NaN A NaN R 15.0 R ... R 0.0 R
1 461829 A NaN A NaN A NaN R 127.0 R ... A NaN A
2 461838 A NaN A NaN A NaN A NaN A ... A NaN A
3 461847 R 8.0 R 26.0 R 31.0 R 7.0 R ... A NaN A
4 461856 A NaN A NaN A NaN R 195.0 R ... A NaN A
.. ... .. ... .. ... .. ... .. ... .. ... ... ... ...
66 475273 A NaN A NaN A NaN A NaN A ... A NaN A
67 475282 A NaN A NaN A NaN R 8.0 R ... A NaN A
68 475325 A NaN A NaN A NaN R 222.0 R ... A NaN A
69 475398 A NaN A NaN A NaN R 0.0 R ... R 0.0 R
70 475404 A NaN A NaN A NaN A NaN A ... A NaN A
7.1 R.13 0.4 R.14 0.5 R.15 14
0 4.0 R 0.0 R 0.0 R 15
1 NaN A NaN A NaN R 10
2 NaN A NaN A NaN R 20
3 NaN A NaN A NaN R 15
4 NaN A NaN A NaN R 30
.. ... ... ... ... ... ... ..
66 NaN A NaN A NaN R 9
67 NaN A NaN A NaN R 12
68 NaN A NaN A NaN R 15
69 2.0 R 2.0 R 100.0 R 4
70 NaN A NaN A NaN R 12
[71 rows x 33 columns],
475413 A Unnamed: 0 A.1 Unnamed: 1 A.2 Unnamed: 2 R 16 R.1 ... \
0 475422 A NaN A NaN A NaN R 0.0 R ...
1 475431 A NaN A NaN A NaN A NaN A ...
2 475459 A NaN A NaN A NaN R 491.0 R ...
3 475468 A NaN A NaN A NaN R 16.0 R ...
4 475477 R 15.0 R 35.0 R 43.0 R 6.0 R ...
.. ... .. ... .. ... .. ... .. ... .. ...
66 478616 A NaN A NaN A NaN R 20.0 R ...
67 478634 A NaN A NaN A NaN R 4.0 Z ...
68 478661 A NaN A NaN A NaN R 17.0 R ...
69 478917 A NaN A NaN A NaN R 31.0 Z ...
70 478953 A NaN A NaN A NaN R 39.0 R ...
Z.1 0.3 R.7 2.1 R.8 2.2 R.9 100 R.10 13
0 R 0.0 R 0.0 R 0.0 A NaN R 5
1 A NaN A NaN A NaN A NaN R 9
2 R 0.0 R 16.0 R 14.0 R 88.0 R 20
3 R 0.0 R 19.0 R 17.0 R 89.0 R 13
4 R 0.0 R 1.0 R 0.0 R 0.0 R 9
.. ... ... ... ... ... ... ... ... ... ..
66 Z 0.0 R 7.0 R 3.0 R 43.0 R 14
67 A NaN A NaN A NaN A NaN R 16
68 R 0.0 R 6.0 R 4.0 R 67.0 R 11
69 A NaN A NaN A NaN A NaN R 10
70 A NaN A NaN A NaN A NaN R 14
[71 rows x 33 columns],
479062 A Unnamed: 0 A.1 Unnamed: 1 A.2 Unnamed: 2 A.3 Unnamed: 3 A.4 \
0 479248 A NaN A NaN A NaN R 81.0 R
1 479424 A NaN A NaN A NaN R 43.0 R
2 479965 A NaN A NaN A NaN R 4.0 R
3 479974 A NaN A NaN A NaN R 29.0 Z
4 479983 A NaN A NaN A NaN R 9.0 R
.. ... .. ... .. ... .. ... .. ... ..
66 481368 A NaN A NaN A NaN R 11.0 R
67 481386 A NaN A NaN A NaN R 2.0 Z
68 481401 R 3.0 R 23.0 R 13.0 R 0.0 Z
69 481410 R 21.0 R 26.0 R 81.0 R 16.0 R
70 481429 A NaN A NaN A NaN R 49.0 R
... A.11 Unnamed: 11 A.12 Unnamed: 12 A.13 Unnamed: 13 A.14 \
0 ... R 0.0 R 3.0 R 2.0 R
1 ... Z 0.0 R 0.0 Z 0.0 A
2 ... A NaN A NaN A NaN A
3 ... A NaN A NaN A NaN A
4 ... Z 0.0 R 0.0 Z 0.0 A
.. ... ... ... ... ... ... ... ...
66 ... A NaN A NaN A NaN A
67 ... Z 0.0 R 32.0 R 29.0 R
68 ... Z 0.0 R 11.0 R 8.0 R
69 ... A NaN A NaN A NaN A
70 ... A NaN A NaN A NaN A
Unnamed: 14 R 6
0 67.0 R 15
1 NaN R 15
2 NaN R 12
3 NaN R 20
4 NaN R 15
.. ... .. ..
66 NaN R 9
67 91.0 R 18
68 73.0 R 13
69 NaN R 17
70 NaN R 30
[71 rows x 33 columns],
481438 R 17 R.1 18 R.2 94 R.3 28 R.4 ... A.2 Unnamed: 2 A.3 \
0 481447 A NaN A NaN A NaN A NaN A ... A NaN A
1 481456 A NaN A NaN A NaN R 3.0 R ... R 0.0 R
2 481465 A NaN A NaN A NaN R 3.0 R ... A NaN A
3 481474 A NaN A NaN A NaN R 21.0 R ... R 0.0 R
4 481483 A NaN A NaN A NaN R 39.0 R ... R 0.0 R
.. ... .. .. .. .. .. .. .. ... .. ... ... ... ...
66 483221 A NaN A NaN A NaN R 2.0 R ... A NaN A
67 483230 A NaN A NaN A NaN A NaN A ... A NaN A
68 483258 A NaN A NaN A NaN R 7.0 Z ... A NaN A
69 483276 A NaN A NaN A NaN R 29.0 R ... A NaN A
70 483328 A NaN A NaN A NaN R 12.0 Z ... Z 0.0 R
Unnamed: 3 A.4 Unnamed: 4 A.5 Unnamed: 5 R.9 6
0 NaN A NaN A NaN R 12
1 4.0 R 3.0 R 75.0 R 6
2 NaN A NaN A NaN R 10
3 5.0 R 5.0 R 100.0 R 15
4 18.0 R 14.0 R 78.0 R 15
.. ... ... ... ... ... ... ..
66 NaN A NaN A NaN R 4
67 NaN A NaN A NaN R 11
68 NaN A NaN A NaN R 20
69 NaN A NaN A NaN R 12
70 3.0 R 2.0 R 67.0 R 15
[71 rows x 33 columns],
483337 A Unnamed: 0 A.1 Unnamed: 1 A.2 Unnamed: 2 R 14 Z ... \
0 483346 A NaN A NaN A NaN R 4.0 R ...
1 483355 A NaN A NaN A NaN R 12.0 R ...
2 483364 A NaN A NaN A NaN R 9.0 R ...
3 483373 A NaN A NaN A NaN R 1.0 Z ...
4 483382 A NaN A NaN A NaN A NaN A ...
.. ... .. ... .. ... .. ... .. ... .. ...
66 484729 A NaN A NaN A NaN A NaN A ...
67 484756 A NaN A NaN A NaN R 2.0 R ...
68 484783 A NaN A NaN A NaN A NaN A ...
69 484826 A NaN A NaN A NaN R 17.0 Z ...
70 484835 R 22.0 R 64.0 R 34.0 R 2.0 R ...
Z.3 0.3 R.5 4.1 R.6 1 R.7 25 R.8 15
0 R 0.0 R 0.0 R 0.0 A NaN R 8
1 A NaN A NaN A NaN A NaN R 10
2 A NaN A NaN A NaN A NaN R 9
3 Z 0.0 R 0.0 Z 0.0 A NaN R 20
4 A NaN A NaN A NaN A NaN R 20
.. ... ... ... ... ... ... ... .. ... ..
66 A NaN A NaN A NaN A NaN R 4
67 A NaN A NaN A NaN A NaN R 8
68 A NaN A NaN A NaN A NaN R 5
69 A NaN A NaN A NaN A NaN R 12
70 A NaN A NaN A NaN A NaN R 14
[71 rows x 33 columns],
484862 A Unnamed: 0 A.1 Unnamed: 1 A.2 Unnamed: 2 A.3 Unnamed: 3 A.4 \
0 484871 R 35.0 R 35.0 R 100.0 R 33.0 Z
1 484899 A NaN A NaN A NaN R 59.0 Z
2 484905 R 327.0 R 985.0 R 33.0 R 390.0 R
3 484923 A NaN A NaN A NaN A NaN A
4 484932 R 321.0 R 662.0 R 48.0 R 389.0 R
.. ... .. ... .. ... .. ... .. ... ..
66 486406 A NaN A NaN A NaN R 3.0 R
67 486415 A NaN A NaN A NaN R 46.0 R
68 486424 A NaN A NaN A NaN R 33.0 R
69 486442 A NaN A NaN A NaN R 5.0 Z
70 486488 R 2.0 R 12.0 R 17.0 R 1.0 R
... A.11 Unnamed: 11 A.12 Unnamed: 12 A.13 Unnamed: 13 A.14 \
0 ... A NaN A NaN A NaN A
1 ... A NaN A NaN A NaN A
2 ... R 0.0 R 34.0 R 12.0 R
3 ... A NaN A NaN A NaN A
4 ... R 0.0 R 136.0 R 49.0 R
.. ... ... ... ... ... ... ... ...
66 ... A NaN A NaN A NaN A
67 ... A NaN A NaN A NaN A
68 ... R 0.0 R 3.0 R 3.0 R
69 ... A NaN A NaN A NaN A
70 ... R 0.0 R 0.0 R 0.0 A
Unnamed: 14 R 5
0 NaN R 16
1 NaN R 14
2 35.0 R 17
3 NaN R 12
4 36.0 R 12
.. ... .. ..
66 NaN R 3
67 NaN R 30
68 100.0 R 15
69 NaN R 20
70 NaN R 5
[71 rows x 33 columns],
486497 A Unnamed: 0 A.1 Unnamed: 1 A.2 Unnamed: 2 R 9 R.1 ... \
0 486503 A NaN A NaN A NaN R 14.0 R ...
1 486512 A NaN A NaN A NaN R 30.0 R ...
2 486530 A NaN A NaN A NaN R 10.0 Z ...
3 486558 A NaN A NaN A NaN R 29.0 Z ...
4 486567 A NaN A NaN A NaN R 39.0 Z ...
.. ... .. ... .. ... .. ... .. ... .. ...
66 487852 A NaN A NaN A NaN A NaN A ...
67 487861 R 63.0 R 86.0 R 73.0 R 0.0 R ...
68 487889 A NaN A NaN A NaN A NaN A ...
69 487898 A NaN A NaN A NaN R 7.0 Z ...
70 487904 A NaN A NaN A NaN R 12.0 R ...
A.5 Unnamed: 5 A.6 Unnamed: 6 A.7 Unnamed: 7 A.8 Unnamed: 8 R.6 25
0 R 0.0 R 0.0 R 0.0 A NaN R 14
1 A NaN A NaN A NaN A NaN R 30
2 A NaN A NaN A NaN A NaN R 8
3 A NaN A NaN A NaN A NaN R 12
4 A NaN A NaN A NaN A NaN R 12
.. ... ... ... ... ... ... ... ... ... ..
66 A NaN A NaN A NaN A NaN R 5
67 R 0.0 R 0.0 Z 0.0 A NaN R 22
68 A NaN A NaN A NaN A NaN R 10
69 Z 0.0 R 19.0 R 9.0 R 47.0 R 9
70 A NaN A NaN A NaN A NaN R 10
[71 rows x 33 columns],
487913 A Unnamed: 0 A.1 Unnamed: 1 A.2 Unnamed: 2 R 0 R.1 ... \
0 487922 A NaN A NaN A NaN R 5.0 R ...
1 487959 A NaN A NaN A NaN R 27.0 R ...
2 487968 A NaN A NaN A NaN R 64.0 R ...
3 487977 A NaN A NaN A NaN R 61.0 R ...
4 487995 A NaN A NaN A NaN A NaN A ...
.. ... .. ... .. ... .. ... .. ... .. ...
66 489247 A NaN A NaN A NaN R 3.0 R ...
67 489256 A NaN A NaN A NaN R 204.0 R ...
68 489283 A NaN A NaN A NaN R 171.0 Z ...
69 489344 A NaN A NaN A NaN R 2.0 R ...
70 489353 R 1.0 R 35.0 R 3.0 R 0.0 R ...
R.7 0.7 R.8 0.8 R.9 0.9 A.4 Unnamed: 4 R.10 20
0 A NaN A NaN A NaN A NaN R 23
1 R 0.0 R 0.0 R 0.0 A NaN R 20
2 A NaN A NaN A NaN A NaN R 10
3 R 0.0 R 151.0 R 107.0 R 71.0 R 58
4 A NaN A NaN A NaN A NaN R 15
.. ... ... ... ... ... ... ... ... ... ..
66 R 0.0 R 5.0 R 4.0 R 80.0 R 3
67 Z 0.0 R 4.0 R 4.0 R 100.0 R 25
68 A NaN A NaN A NaN A NaN R 24
69 R 0.0 R 0.0 R 0.0 A NaN R 13
70 R 0.0 R 1.0 R 1.0 R 100.0 R 11
[71 rows x 33 columns],
489371 A Unnamed: 0 A.1 Unnamed: 1 A.2 Unnamed: 2 R 75 R.1 ... \
0 489760 A NaN A NaN A NaN R 61.0 Z ...
1 489779 A NaN A NaN A NaN R 3.0 R ...
2 489812 A NaN A NaN A NaN R 23.0 R ...
3 489830 A NaN A NaN A NaN R 17.0 R ...
4 489937 R 65.0 R 178.0 R 37.0 R 59.0 R ...
.. ... .. ... .. ... .. ... .. ... .. ...
66 490975 A NaN A NaN A NaN R 26.0 Z ...
67 491057 R 8.0 R 69.0 R 12.0 R 3.0 R ...
68 491066 A NaN A NaN A NaN R 10.0 R ...
69 491075 A NaN A NaN A NaN R 24.0 R ...
70 491084 A NaN A NaN A NaN R 38.0 R ...
A.5 Unnamed: 5 A.6 Unnamed: 6 A.7 Unnamed: 7 A.8 Unnamed: 8 R.6 13
0 A NaN A NaN A NaN A NaN R 5
1 Z 0.0 R 439.0 R 144.0 R 33.0 R 28
2 A NaN A NaN A NaN A NaN R 10
3 A NaN A NaN A NaN A NaN R 19
4 R 0.0 R 1.0 R 0.0 R 0.0 R 10
.. ... ... ... ... ... ... ... ... ... ..
66 Z 0.0 R 2.0 R 1.0 R 50.0 R 31
67 A NaN A NaN A NaN A NaN R 19
68 R 0.0 R 11.0 R 1.0 R 9.0 R 9
69 A NaN A NaN A NaN A NaN R 8
70 A NaN A NaN A NaN A NaN R 10
[71 rows x 33 columns],
491136 A Unnamed: 0 A.1 Unnamed: 1 A.2 Unnamed: 2 R 35 R.1 ... \
0 491145 A NaN A NaN A NaN R 33.0 R ...
1 491181 A NaN A NaN A NaN R 2.0 R ...
2 491215 A NaN A NaN A NaN A NaN A ...
3 491224 A NaN A NaN A NaN R 1.0 Z ...
4 491233 A NaN A NaN A NaN R 9.0 R ...
.. ... .. ... .. ... .. ... .. ... .. ...
66 492281 A NaN A NaN A NaN R 4.0 R ...
67 492306 A NaN A NaN A NaN A NaN A ...
68 492315 A NaN A NaN A NaN A NaN A ...
69 492324 A NaN A NaN A NaN A NaN A ...
70 492360 A NaN A NaN A NaN R 6.0 R ...
Z.1 0.3 R.7 4.1 R.8 1 R.9 25 R.10 17
0 Z 0.0 R 9.0 R 6.0 R 67.0 R 16
1 R 0.0 R 1.0 R 0.0 R 0.0 R 16
2 A NaN A NaN A NaN A NaN R 11
3 Z 0.0 R 4.0 R 4.0 R 100.0 R 18
4 R 0.0 R 1.0 R 0.0 R 0.0 R 20
.. ... ... ... ... ... ... ... ... ... ..
66 A NaN A NaN A NaN A NaN R 2
67 A NaN A NaN A NaN A NaN R 15
68 A NaN A NaN A NaN A NaN R 11
69 A NaN A NaN A NaN A NaN R 18
70 R 0.0 R 2.0 R 2.0 R 100.0 R 8
[71 rows x 33 columns],
492379 A Unnamed: 0 A.1 Unnamed: 1 A.2 Unnamed: 2 A.3 Unnamed: 3 A.4 \
0 492397 A NaN A NaN A NaN R 8.0 R
1 492421 A NaN A NaN A NaN R 9.0 Z
2 492449 A NaN A NaN A NaN R 46.0 R
3 492476 R 7.0 R 60.0 R 12.0 R 0.0 R
4 492591 A NaN A NaN A NaN R 2.0 R
.. ... .. ... .. ... .. ... .. ... ..
66 494250 A NaN A NaN A NaN R 8.0 R
67 494269 A NaN A NaN A NaN Z 0.0 Z
68 494278 R 11.0 R 66.0 R 17.0 R 1.0 R
69 494287 R 27.0 R 101.0 R 27.0 R 0.0 R
70 494357 A NaN A NaN A NaN R 151.0 R
... A.11 Unnamed: 11 A.12 Unnamed: 12 A.13 Unnamed: 13 A.14 \
0 ... A NaN A NaN A NaN A
1 ... A NaN A NaN A NaN A
2 ... A NaN A NaN A NaN A
3 ... R 0.0 R 1.0 R 0.0 R
4 ... A NaN A NaN A NaN A
.. ... ... ... ... ... ... ... ...
66 ... A NaN A NaN A NaN A
67 ... Z 0.0 R 0.0 R 0.0 A
68 ... R 0.0 R 0.0 R 0.0 A
69 ... R 0.0 R 0.0 R 0.0 A
70 ... A NaN A NaN A NaN A
Unnamed: 14 R 12
0 NaN R 14
1 NaN R 20
2 NaN R 15
3 0.0 R 13
4 NaN R 7
.. ... .. ..
66 NaN R 18
67 NaN R 1
68 NaN R 19
69 NaN R 16
70 NaN R 30
[71 rows x 33 columns],
494436 A Unnamed: 0 A.1 Unnamed: 1 A.2 Unnamed: 2 R 30 Z ... \
0 494463 A NaN A NaN A NaN R 146.0 R ...
1 494472 A NaN A NaN A NaN R 0.0 R ...
2 494524 A NaN A NaN A NaN R 25.0 R ...
3 494588 A NaN A NaN A NaN R 37.0 R ...
4 494621 A NaN A NaN A NaN A NaN A ...
.. ... .. ... .. ... .. ... .. ... .. ...
66 495776 A NaN A NaN A NaN R 0.0 R ...
67 495794 A NaN A NaN A NaN R 13.0 Z ...
68 495837 A NaN A NaN A NaN R 59.0 R ...
69 495916 A NaN A NaN A NaN R 1.0 Z ...
70 495925 A NaN A NaN A NaN R 35.0 R ...
A.5 Unnamed: 5 A.6 Unnamed: 6 A.7 Unnamed: 7 A.8 Unnamed: 8 R.4 18
0 A NaN A NaN A NaN A NaN R 41
1 R 0.0 R 2.0 R 1.0 R 50.0 R 5
2 R 0.0 R 17.0 R 14.0 R 82.0 R 14
3 A NaN A NaN A NaN A NaN R 10
4 Z 0.0 R 0.0 R 0.0 A NaN R 6
.. ... ... ... ... ... ... ... ... ... ..
66 A NaN A NaN A NaN A NaN R 12
67 Z 0.0 R 1.0 R 1.0 R 100.0 R 17
68 A NaN A NaN A NaN A NaN R 21
69 Z 0.0 R 0.0 Z 0.0 A NaN R 2
70 A NaN A NaN A NaN A NaN R 43
[71 rows x 33 columns],
495934 A Unnamed: 0 A.1 Unnamed: 1 A.2 Unnamed: 2 R 25 R.1 ... \
0 495943 A NaN A NaN A NaN R 14 R ...
1 495952 A NaN A NaN A NaN R 0 R ...
2 495961 A NaN A NaN A NaN R 0 Z ...
3 495970 A NaN A NaN A NaN R 23 R ...
4 495998 A NaN A NaN A NaN R 30 R ...
5 496052 A NaN A NaN A NaN R 3 R ...
6 496061 A NaN A NaN A NaN R 23 R ...
7 496186 A NaN A NaN A NaN R 0 R ...
8 496265 R 11.0 R 13.0 R 85.0 R 1 R ...
9 496283 A NaN A NaN A NaN R 0 Z ...
10 496326 A NaN A NaN A NaN R 0 Z ...
11 496371 A NaN A NaN A NaN R 0 Z ...
12 496423 A NaN A NaN A NaN R 6 R ...
A.5 Unnamed: 5 A.6 Unnamed: 6 A.7 Unnamed: 7 A.8 Unnamed: 8 R.5 43
0 A NaN A NaN A NaN A NaN R 63
1 A NaN A NaN A NaN A NaN R 17
2 A NaN A NaN A NaN A NaN R 28
3 A NaN A NaN A NaN A NaN R 42
4 A NaN A NaN A NaN A NaN R 61
5 R 0.0 R 0.0 R 0.0 A NaN R 3
6 R 0.0 R 4.0 R 0.0 R 0.0 R 25
7 A NaN A NaN A NaN A NaN R 8
8 A NaN A NaN A NaN A NaN R 7
9 Z 0.0 R 0.0 Z 0.0 A NaN R 8
10 Z 0.0 R 0.0 Z 0.0 A NaN R 7
11 A NaN A NaN A NaN A NaN R 16
12 R 0.0 R 0.0 R 0.0 A NaN R 6
[13 rows x 33 columns]]
In [67]:
en = en[0]
In [68]:
en.head()
Out[68]:
| UNITID | XGRCOHR | GRCOHRT | XUGENTER | UGENTER | XPGRCOH | PGRCOHR | XRRFTCT | RRFTCT | XRRFTEX | ... | XRRPTIN | RRPTIN | XRRPTCTA | RRPTCTA | XRET_NM.1 | RET_NMP | XRET_PCP | RET_PCP | XSTUFACR | STUFACR | |
|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|
| 0 | 100654 | R | 1525.0 | R | 1712.0 | R | 89.0 | R | 1688.0 | R | ... | R | 0.0 | R | 6.0 | R | 2.0 | R | 33.0 | R | 18 |
| 1 | 100663 | R | 2102.0 | R | 3529.0 | R | 60.0 | R | 2294.0 | R | ... | R | 0.0 | R | 42.0 | R | 20.0 | R | 48.0 | R | 20 |
| 2 | 100690 | A | NaN | A | NaN | A | NaN | R | 2.0 | Z | ... | A | NaN | A | NaN | A | NaN | A | NaN | R | 13 |
| 3 | 100706 | R | 1328.0 | R | 2186.0 | R | 61.0 | R | 1489.0 | R | ... | R | 0.0 | R | 8.0 | R | 2.0 | R | 25.0 | R | 19 |
| 4 | 100724 | R | 926.0 | R | 1123.0 | R | 82.0 | R | 1000.0 | R | ... | R | 0.0 | R | 19.0 | R | 1.0 | R | 5.0 | R | 15 |
5 rows × 33 columns
In [69]:
en.tail()
Out[69]:
| UNITID | XGRCOHR | GRCOHRT | XUGENTER | UGENTER | XPGRCOH | PGRCOHR | XRRFTCT | RRFTCT | XRRFTEX | ... | XRRPTIN | RRPTIN | XRRPTCTA | RRPTCTA | XRET_NM.1 | RET_NMP | XRET_PCP | RET_PCP | XSTUFACR | STUFACR | |
|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|
| 66 | 103927 | A | NaN | A | NaN | A | NaN | R | 41.0 | Z | ... | A | NaN | A | NaN | A | NaN | A | NaN | R | 25 |
| 67 | 103945 | A | NaN | A | NaN | A | NaN | R | 2.0 | Z | ... | A | NaN | A | NaN | A | NaN | A | NaN | R | 4 |
| 68 | 103954 | A | NaN | A | NaN | A | NaN | R | 3.0 | R | ... | A | NaN | A | NaN | A | NaN | A | NaN | R | 20 |
| 69 | 103963 | A | NaN | A | NaN | A | NaN | R | 99.0 | R | ... | R | 0.0 | R | 0.0 | R | 0.0 | A | NaN | R | 10 |
| 70 | 104090 | A | NaN | A | NaN | A | NaN | R | 19.0 | R | ... | R | 0.0 | R | 0.0 | R | 0.0 | A | NaN | R | 24 |
5 rows × 33 columns
Remove Columns that Contain Codes¶
In [70]:
en.columns
# Let's see if we can remove the columns that contain an 'X'
Out[70]:
Index(['UNITID', 'XGRCOHR', 'GRCOHRT', 'XUGENTER', 'UGENTER', 'XPGRCOH',
'PGRCOHR', 'XRRFTCT', 'RRFTCT', 'XRRFTEX', 'RRFTEX', 'XRRFTIN',
'RRFTIN', 'XRRFTCTA', 'RRFTCTA', 'XRET_NM', 'RET_NMF', 'XRET_PCF',
'RET_PCF', 'XRRPTCT', 'RRPTCT', 'XRRPTEX', 'RRPTEX', 'XRRPTIN',
'RRPTIN', 'XRRPTCTA', 'RRPTCTA', 'XRET_NM.1', 'RET_NMP', 'XRET_PCP',
'RET_PCP', 'XSTUFACR', 'STUFACR'],
dtype='object')
In [71]:
cols_to_keep = []
for c in en.columns:
if 'X' not in c:
cols_to_keep.append(c)
In [72]:
cols_to_keep = []
for c in en.columns:
if 'X' not in c:
cols_to_keep.append(c)
In [73]:
cols_to_keep
Out[73]:
['UNITID', 'GRCOHRT', 'UGENTER', 'PGRCOHR', 'RRFTCT', 'RRFTIN', 'RRFTCTA', 'RET_NMF', 'RET_PCF', 'RRPTCT', 'RRPTIN', 'RRPTCTA', 'RET_NMP', 'RET_PCP', 'STUFACR']
In [74]:
en2 = en[cols_to_keep]
In [75]:
en2.iloc[:, 1:].describe()
Out[75]:
| GRCOHRT | UGENTER | PGRCOHR | RRFTCT | RRFTIN | RRFTCTA | RET_NMF | RET_PCF | RRPTCT | RRPTIN | RRPTCTA | RET_NMP | RET_PCP | STUFACR | |
|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|
| count | 56.000000 | 56.000000 | 56.000000 | 69.000000 | 69.0 | 69.000000 | 69.000000 | 68.000000 | 57.000000 | 57.0 | 57.000000 | 57.000000 | 50.000000 | 71.000000 |
| mean | 688.464286 | 1279.821429 | 50.375000 | 631.014493 | 0.0 | 630.811594 | 460.000000 | 67.588235 | 91.578947 | 0.0 | 91.526316 | 40.649123 | 42.140000 | 15.014085 |
| std | 1085.246230 | 1481.970201 | 24.002699 | 1032.230758 | 0.0 | 1032.015992 | 900.678502 | 13.942564 | 151.390336 | 0.0 | 151.322162 | 81.625340 | 24.603808 | 5.362550 |
| min | 1.000000 | 12.000000 | 6.000000 | 0.000000 | 0.0 | 0.000000 | 0.000000 | 34.000000 | 0.000000 | 0.0 | 0.000000 | 0.000000 | 0.000000 | 4.000000 |
| 25% | 188.000000 | 341.500000 | 33.750000 | 66.000000 | 0.0 | 66.000000 | 41.000000 | 58.500000 | 4.000000 | 0.0 | 4.000000 | 2.000000 | 29.750000 | 12.000000 |
| 50% | 354.000000 | 789.000000 | 43.000000 | 320.000000 | 0.0 | 320.000000 | 208.000000 | 65.000000 | 24.000000 | 0.0 | 24.000000 | 9.000000 | 38.000000 | 15.000000 |
| 75% | 898.250000 | 1544.750000 | 69.750000 | 789.000000 | 0.0 | 789.000000 | 435.000000 | 77.250000 | 133.000000 | 0.0 | 133.000000 | 42.000000 | 50.750000 | 18.000000 |
| max | 6466.000000 | 7948.000000 | 97.000000 | 6734.000000 | 0.0 | 6733.000000 | 5873.000000 | 100.000000 | 761.000000 | 0.0 | 760.000000 | 462.000000 | 100.000000 | 35.000000 |
In [76]:
en2.iloc[:,1:].corr()
Out[76]:
| GRCOHRT | UGENTER | PGRCOHR | RRFTCT | RRFTIN | RRFTCTA | RET_NMF | RET_PCF | RRPTCT | RRPTIN | RRPTCTA | RET_NMP | RET_PCP | STUFACR | |
|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|
| GRCOHRT | 1.000000 | 0.928805 | 0.319417 | 0.994914 | NaN | 0.994905 | 0.994323 | 0.379099 | 0.043763 | NaN | 0.042785 | 0.080625 | 0.162304 | 0.484789 |
| UGENTER | 0.928805 | 1.000000 | 0.125399 | 0.932618 | NaN | 0.932670 | 0.909415 | 0.293813 | 0.343800 | NaN | 0.343019 | 0.376257 | 0.147883 | 0.599959 |
| PGRCOHR | 0.319417 | 0.125399 | 1.000000 | 0.301361 | NaN | 0.301289 | 0.307085 | 0.139696 | -0.306241 | NaN | -0.306675 | -0.279614 | -0.129778 | 0.098439 |
| RRFTCT | 0.994914 | 0.932618 | 0.301361 | 1.000000 | NaN | 1.000000 | 0.991601 | 0.234453 | 0.064328 | NaN | 0.063448 | 0.032688 | 0.103813 | 0.253491 |
| RRFTIN | NaN | NaN | NaN | NaN | NaN | NaN | NaN | NaN | NaN | NaN | NaN | NaN | NaN | NaN |
| RRFTCTA | 0.994905 | 0.932670 | 0.301289 | 1.000000 | NaN | 1.000000 | 0.991605 | 0.234525 | 0.064436 | NaN | 0.063556 | 0.032769 | 0.103779 | 0.253546 |
| RET_NMF | 0.994323 | 0.909415 | 0.307085 | 0.991601 | NaN | 0.991605 | 1.000000 | 0.298123 | 0.006206 | NaN | 0.005252 | -0.000583 | 0.130204 | 0.237952 |
| RET_PCF | 0.379099 | 0.293813 | 0.139696 | 0.234453 | NaN | 0.234525 | 0.298123 | 1.000000 | -0.211501 | NaN | -0.212017 | -0.050746 | 0.100858 | 0.027222 |
| RRPTCT | 0.043763 | 0.343800 | -0.306241 | 0.064328 | NaN | 0.064436 | 0.006206 | -0.211501 | 1.000000 | NaN | 0.999998 | 0.896768 | 0.065188 | 0.276120 |
| RRPTIN | NaN | NaN | NaN | NaN | NaN | NaN | NaN | NaN | NaN | NaN | NaN | NaN | NaN | NaN |
| RRPTCTA | 0.042785 | 0.343019 | -0.306675 | 0.063448 | NaN | 0.063556 | 0.005252 | -0.212017 | 0.999998 | NaN | 1.000000 | 0.896813 | 0.064872 | 0.275766 |
| RET_NMP | 0.080625 | 0.376257 | -0.279614 | 0.032688 | NaN | 0.032769 | -0.000583 | -0.050746 | 0.896768 | NaN | 0.896813 | 1.000000 | 0.249742 | 0.178385 |
| RET_PCP | 0.162304 | 0.147883 | -0.129778 | 0.103813 | NaN | 0.103779 | 0.130204 | 0.100858 | 0.065188 | NaN | 0.064872 | 0.249742 | 1.000000 | 0.060263 |
| STUFACR | 0.484789 | 0.599959 | 0.098439 | 0.253491 | NaN | 0.253546 | 0.237952 | 0.027222 | 0.276120 | NaN | 0.275766 | 0.178385 | 0.060263 | 1.000000 |
In [77]:
# Let's clear the heatmap for duplicate correlation values
mask = np.zeros_like(en2.iloc[:,1:].corr())
mask[np.triu_indices_from(mask)] = True
# Time to plot!
with sns.axes_style("white"):
f, ax = plt.subplots(figsize = (15,9))
sns.heatmap(en2.iloc[:,1:].corr(),mask=mask,
cmap = 'RdBu')
In [78]:
mask = np.zeros_like(en2.iloc[:,1:].corr())
mask[np.triu_indices_from(mask)] = True
with sns.axes_style("white"):
f, ax = plt.subplots(figsize = (15,9))
sns.heatmap(en2.iloc[:,1:].corr(),mask=mask,
cmap = 'RdBu')
Changing a Data Type¶
In [79]:
en2.info()
<class 'pandas.core.frame.DataFrame'> RangeIndex: 71 entries, 0 to 70 Data columns (total 15 columns): # Column Non-Null Count Dtype --- ------ -------------- ----- 0 UNITID 71 non-null int64 1 GRCOHRT 56 non-null float64 2 UGENTER 56 non-null float64 3 PGRCOHR 56 non-null float64 4 RRFTCT 69 non-null float64 5 RRFTIN 69 non-null float64 6 RRFTCTA 69 non-null float64 7 RET_NMF 69 non-null float64 8 RET_PCF 68 non-null float64 9 RRPTCT 57 non-null float64 10 RRPTIN 57 non-null float64 11 RRPTCTA 57 non-null float64 12 RET_NMP 57 non-null float64 13 RET_PCP 50 non-null float64 14 STUFACR 71 non-null int64 dtypes: float64(13), int64(2) memory usage: 8.4 KB
In [80]:
en2.loc['STUFACR'] = en2.STUFACR.astype('float')
In [81]:
en2.info()
<class 'pandas.core.frame.DataFrame'> Index: 72 entries, 0 to STUFACR Data columns (total 15 columns): # Column Non-Null Count Dtype --- ------ -------------- ----- 0 UNITID 71 non-null float64 1 GRCOHRT 56 non-null float64 2 UGENTER 56 non-null float64 3 PGRCOHR 56 non-null float64 4 RRFTCT 69 non-null float64 5 RRFTIN 69 non-null float64 6 RRFTCTA 69 non-null float64 7 RET_NMF 69 non-null float64 8 RET_PCF 68 non-null float64 9 RRPTCT 57 non-null float64 10 RRPTIN 57 non-null float64 11 RRPTCTA 57 non-null float64 12 RET_NMP 57 non-null float64 13 RET_PCP 50 non-null float64 14 STUFACR 71 non-null float64 dtypes: float64(15) memory usage: 9.0+ KB
Checking for NAs¶
In [82]:
for n in en2:
print("The percent of missing values in {0} is {1}".format(n, en2[[n]].isna().mean().round(2)))
The percent of missing values in UNITID is UNITID 0.01 dtype: float64 The percent of missing values in GRCOHRT is GRCOHRT 0.22 dtype: float64 The percent of missing values in UGENTER is UGENTER 0.22 dtype: float64 The percent of missing values in PGRCOHR is PGRCOHR 0.22 dtype: float64 The percent of missing values in RRFTCT is RRFTCT 0.04 dtype: float64 The percent of missing values in RRFTIN is RRFTIN 0.04 dtype: float64 The percent of missing values in RRFTCTA is RRFTCTA 0.04 dtype: float64 The percent of missing values in RET_NMF is RET_NMF 0.04 dtype: float64 The percent of missing values in RET_PCF is RET_PCF 0.06 dtype: float64 The percent of missing values in RRPTCT is RRPTCT 0.21 dtype: float64 The percent of missing values in RRPTIN is RRPTIN 0.21 dtype: float64 The percent of missing values in RRPTCTA is RRPTCTA 0.21 dtype: float64 The percent of missing values in RET_NMP is RET_NMP 0.21 dtype: float64 The percent of missing values in RET_PCP is RET_PCP 0.31 dtype: float64 The percent of missing values in STUFACR is STUFACR 0.01 dtype: float64
In [83]:
for n in en2:
print("The percent of missing values in {0} is {1}".format(n, en2[[n]].isna().mean()))
The percent of missing values in UNITID is UNITID 0.013889 dtype: float64 The percent of missing values in GRCOHRT is GRCOHRT 0.222222 dtype: float64 The percent of missing values in UGENTER is UGENTER 0.222222 dtype: float64 The percent of missing values in PGRCOHR is PGRCOHR 0.222222 dtype: float64 The percent of missing values in RRFTCT is RRFTCT 0.041667 dtype: float64 The percent of missing values in RRFTIN is RRFTIN 0.041667 dtype: float64 The percent of missing values in RRFTCTA is RRFTCTA 0.041667 dtype: float64 The percent of missing values in RET_NMF is RET_NMF 0.041667 dtype: float64 The percent of missing values in RET_PCF is RET_PCF 0.055556 dtype: float64 The percent of missing values in RRPTCT is RRPTCT 0.208333 dtype: float64 The percent of missing values in RRPTIN is RRPTIN 0.208333 dtype: float64 The percent of missing values in RRPTCTA is RRPTCTA 0.208333 dtype: float64 The percent of missing values in RET_NMP is RET_NMP 0.208333 dtype: float64 The percent of missing values in RET_PCP is RET_PCP 0.305556 dtype: float64 The percent of missing values in STUFACR is STUFACR 0.013889 dtype: float64
Filling Missing Values with the Mean¶
In [84]:
ret_mean = en2.RET_PCF.mean().round(2)
ret_na = en2.RET_PCF.isna().mean().round(2)
print('The mean for retention is {0} and the missing values is {1}'.format(ret_mean, ret_na))
The mean for retention is 67.59 and the missing values is 0.06
In [85]:
en2['RET_PCF'].fillna(en2.RET_PCF.mean(), inplace=True)
In [86]:
ret_mean = en2.RET_PCF.mean().round(2)
ret_na = en2.RET_PCF.isna().mean().round(2)
print('The mean for retention is {0} and the missing values is {1}'.format(ret_mean, ret_na))
The mean for retention is 67.59 and the missing values is 0.0
Create a Feature¶
In [87]:
en2['Higher_Than_Avg_Ret_Rate'] = en2.RET_PCF > en.RET_PCF.mean()
en2['Ret_Index'] = (en2.RET_PCF-en.RET_PCF.mean())/en2.RET_PCF.std()
In [88]:
en2.head()
Out[88]:
| UNITID | GRCOHRT | UGENTER | PGRCOHR | RRFTCT | RRFTIN | RRFTCTA | RET_NMF | RET_PCF | RRPTCT | RRPTIN | RRPTCTA | RET_NMP | RET_PCP | STUFACR | Higher_Than_Avg_Ret_Rate | Ret_Index | |
|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|
| 0 | 100654.0 | 1525.0 | 1712.0 | 89.0 | 1688.0 | 0.0 | 1686.0 | 911.0 | 54.0 | 6.0 | 0.0 | 6.0 | 2.0 | 33.0 | 18.0 | False | -1.003257 |
| 1 | 100663.0 | 2102.0 | 3529.0 | 60.0 | 2294.0 | 0.0 | 2294.0 | 1982.0 | 86.0 | 42.0 | 0.0 | 42.0 | 20.0 | 48.0 | 20.0 | True | 1.359392 |
| 2 | 100690.0 | NaN | NaN | NaN | 2.0 | 0.0 | 2.0 | 1.0 | 50.0 | NaN | NaN | NaN | NaN | NaN | 13.0 | False | -1.298588 |
| 3 | 100706.0 | 1328.0 | 2186.0 | 61.0 | 1489.0 | 0.0 | 1489.0 | 1218.0 | 82.0 | 8.0 | 0.0 | 8.0 | 2.0 | 25.0 | 19.0 | True | 1.064060 |
| 4 | 100724.0 | 926.0 | 1123.0 | 82.0 | 1000.0 | 0.0 | 998.0 | 619.0 | 62.0 | 19.0 | 0.0 | 19.0 | 1.0 | 5.0 | 15.0 | False | -0.412595 |
In [89]:
en2[['Higher_Than_Avg_Ret_Rate', 'Ret_Index']][60:70]
Out[89]:
| Higher_Than_Avg_Ret_Rate | Ret_Index | |
|---|---|---|
| 60 | True | 0.990228 |
| 61 | False | 0.000000 |
| 62 | True | 0.251900 |
| 63 | False | -0.043431 |
| 64 | True | 0.325733 |
| 65 | False | -0.634093 |
| 66 | True | 0.768729 |
| 67 | True | 2.393050 |
| 68 | True | 2.393050 |
| 69 | False | -1.372421 |
In [90]:
en2.Higher_Than_Avg_Ret_Rate.mean()
Out[90]:
0.4166666666666667
In [91]:
en2.Ret_Index.mean()
Out[91]:
-3.762422472340808e-16
In [92]:
grouped_en = en2[['Ret_Index', 'Higher_Than_Avg_Ret_Rate']].groupby('Higher_Than_Avg_Ret_Rate')
grouped_en.describe()
Out[92]:
| Ret_Index | ||||||||
|---|---|---|---|---|---|---|---|---|
| count | mean | std | min | 25% | 50% | 75% | max | |
| Higher_Than_Avg_Ret_Rate | ||||||||
| False | 42.0 | -0.668631 | 0.512287 | -2.479912 | -0.929424 | -0.634093 | -0.338762 | 0.00000 |
| True | 30.0 | 0.936084 | 0.723393 | 0.030402 | 0.418024 | 0.768729 | 1.285559 | 2.39305 |
In [93]:
grouped_en.mean().plot(kind = 'bar')
plt.show()
Filtering¶
In [94]:
code = pd.read_excel('IPEDS201920Tablesdoc.xlsx', sheet_name= 'valueSets19')
In [95]:
code.head()
Out[95]:
| SurveyOrder | Tablenumber | TableName | varNumber | varOrder | varName | Codevalue | Frequency | Percent | valueOrder | valueLabel | varTitle | |
|---|---|---|---|---|---|---|---|---|---|---|---|---|
| 0 | 10 | 10 | HD2019 | 10016 | 7 | STABBR | AL | 83.0 | 1.27 | 1 | Alabama | State abbreviation |
| 1 | 10 | 10 | HD2019 | 10016 | 7 | STABBR | AK | 10.0 | 0.15 | 2 | Alaska | State abbreviation |
| 2 | 10 | 10 | HD2019 | 10016 | 7 | STABBR | AZ | 117.0 | 1.78 | 3 | Arizona | State abbreviation |
| 3 | 10 | 10 | HD2019 | 10016 | 7 | STABBR | AR | 88.0 | 1.34 | 4 | Arkansas | State abbreviation |
| 4 | 10 | 10 | HD2019 | 10016 | 7 | STABBR | CA | 699.0 | 10.66 | 5 | California | State abbreviation |
In [96]:
hd2019var = code[code['TableName'] == 'HD2019']
In [97]:
hd2019var[hd2019var['varName'] == 'SECTOR']
Out[97]:
| SurveyOrder | Tablenumber | TableName | varNumber | varOrder | varName | Codevalue | Frequency | Percent | valueOrder | valueLabel | varTitle | |
|---|---|---|---|---|---|---|---|---|---|---|---|---|
| 136 | 10 | 10 | HD2019 | 10086 | 32 | SECTOR | 0 | 73.0 | 1.11 | 1 | Administrative Unit | Sector of institution |
| 137 | 10 | 10 | HD2019 | 10086 | 32 | SECTOR | 1 | 807.0 | 12.30 | 2 | Public, 4-year or above | Sector of institution |
| 138 | 10 | 10 | HD2019 | 10086 | 32 | SECTOR | 2 | 1685.0 | 25.69 | 3 | Private not-for-profit, 4-year or above | Sector of institution |
| 139 | 10 | 10 | HD2019 | 10086 | 32 | SECTOR | 3 | 390.0 | 5.95 | 4 | Private for-profit, 4-year or above | Sector of institution |
| 140 | 10 | 10 | HD2019 | 10086 | 32 | SECTOR | 4 | 948.0 | 14.45 | 5 | Public, 2-year | Sector of institution |
| 141 | 10 | 10 | HD2019 | 10086 | 32 | SECTOR | 5 | 153.0 | 2.33 | 6 | Private not-for-profit, 2-year | Sector of institution |
| 142 | 10 | 10 | HD2019 | 10086 | 32 | SECTOR | 6 | 620.0 | 9.45 | 7 | Private for-profit, 2-year | Sector of institution |
| 143 | 10 | 10 | HD2019 | 10086 | 32 | SECTOR | 7 | 235.0 | 3.58 | 8 | Public, less-than 2-year | Sector of institution |
| 144 | 10 | 10 | HD2019 | 10086 | 32 | SECTOR | 8 | 64.0 | 0.98 | 9 | Private not-for-profit, less-than 2-year | Sector of institution |
| 145 | 10 | 10 | HD2019 | 10086 | 32 | SECTOR | 9 | 1552.0 | 23.66 | 10 | Private for-profit, less-than 2-year | Sector of institution |
| 146 | 10 | 10 | HD2019 | 10086 | 32 | SECTOR | 99 | 32.0 | 0.49 | 11 | Sector unknown (not active) | Sector of institution |
In [98]:
hd2019var[['Codevalue', 'valueLabel']][hd2019var['varName']== 'SECTOR']
Out[98]:
| Codevalue | valueLabel | |
|---|---|---|
| 136 | 0 | Administrative Unit |
| 137 | 1 | Public, 4-year or above |
| 138 | 2 | Private not-for-profit, 4-year or above |
| 139 | 3 | Private for-profit, 4-year or above |
| 140 | 4 | Public, 2-year |
| 141 | 5 | Private not-for-profit, 2-year |
| 142 | 6 | Private for-profit, 2-year |
| 143 | 7 | Public, less-than 2-year |
| 144 | 8 | Private not-for-profit, less-than 2-year |
| 145 | 9 | Private for-profit, less-than 2-year |
| 146 | 99 | Sector unknown (not active) |
Joining Dataframes¶
In [99]:
sector = hd2019var[['Codevalue', 'valueLabel']][hd2019var['varName']== 'SECTOR']
sector.columns = ['SECTOR', 'SECTOR LABEL']
sector.SECTOR = sector.SECTOR.astype(int)
In [100]:
hd2 = pd.merge(hd, sector, on = 'SECTOR', how = 'left')
In [101]:
hd2.head()
Out[101]:
| UNITID | INSTNM | IALIAS | CITY | STABBR | ZIP | CHFNM | CHFTITLE | OPEID | SECTOR | HBCU | HLOFFER | UGOFFER | SECTOR LABEL | |
|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|
| 0 | 100654 | Alabama A & M University | AAMU | Normal | AL | 35762 | Dr. Andrew Hugine, Jr. | President | 100200 | 1 | 1 | 9 | 1 | Public, 4-year or above |
| 1 | 100663 | University of Alabama at Birmingham | Birmingham | AL | 35294-0110 | Ray L. Watts | President | 105200 | 1 | 2 | 9 | 1 | Public, 4-year or above | |
| 2 | 100690 | Amridge University | Southern Christian University Regions University | Montgomery | AL | 36117-3553 | Michael C.Turner | President | 2503400 | 2 | 2 | 9 | 1 | Private not-for-profit, 4-year or above |
| 3 | 100706 | University of Alabama in Huntsville | UAH University of Alabama Huntsville | Huntsville | AL | 35899 | Darren Dawson | President | 105500 | 1 | 2 | 9 | 1 | Public, 4-year or above |
| 4 | 100724 | Alabama State University | Montgomery | AL | 36104-0271 | Quinton T. Ross | President | 100500 | 1 | 1 | 9 | 1 | Public, 4-year or above |
In [102]:
figsize = (12, 6)
plt.figure(figsize = figsize)
sns.countplot(x = 'SECTOR LABEL', data = hd2)
plt.xlabel("Sector of Institution")
plt.ylabel("Number of Institutions")
plt.title("Count of Institutions by Sector")
plt.xticks(rotation = 90)
plt.show()
In [103]:
figsize = (12, 6)
plt.figure(figsize = figsize)
sns.countplot(x = 'SECTOR LABEL', data = hd2)
plt.xlabel("Sector of Institution")
plt.ylabel("Number of Institutions")
plt.title("Count of Institutions by Sector")
plt.xticks(rotation = 90)
plt.show()
In [104]:
figsize = (12, 6)
plt.figure(figsize = figsize)
sns.countplot(x = 'SECTOR LABEL', data = hd2, hue = 'UGOFFER', palette='Set2')
sns.color_palette('Set2')
plt.xlabel("Sector of Institution")
plt.ylabel("Number of Institutions")
plt.title("Count of Institutions by Sector")
plt.xticks(rotation = 90)
plt.show()
In [105]:
figsize = (12, 6)
plt.figure(figsize = figsize)
sns.countplot(x = 'SECTOR LABEL', data = hd2, hue = 'UGOFFER', palette='Set2')
sns.color_palette('Set2')
plt.xlabel("Sector of Institution")
plt.ylabel("Number of Institutions")
plt.title("Count of Institutions by Sector")
plt.xticks(rotation = 90)
plt.show()
Pivot Tables¶
In [106]:
ids = hd2[['UNITID', 'INSTNM', 'SECTOR LABEL']]
ids.head()
Out[106]:
| UNITID | INSTNM | SECTOR LABEL | |
|---|---|---|---|
| 0 | 100654 | Alabama A & M University | Public, 4-year or above |
| 1 | 100663 | University of Alabama at Birmingham | Public, 4-year or above |
| 2 | 100690 | Amridge University | Private not-for-profit, 4-year or above |
| 3 | 100706 | University of Alabama in Huntsville | Public, 4-year or above |
| 4 | 100724 | Alabama State University | Public, 4-year or above |
In [107]:
print(en2.head())
en2 = pd.merge(en2, ids, on = 'UNITID', how = 'left')
UNITID GRCOHRT UGENTER PGRCOHR RRFTCT RRFTIN RRFTCTA RET_NMF \ 0 100654.0 1525.0 1712.0 89.0 1688.0 0.0 1686.0 911.0 1 100663.0 2102.0 3529.0 60.0 2294.0 0.0 2294.0 1982.0 2 100690.0 NaN NaN NaN 2.0 0.0 2.0 1.0 3 100706.0 1328.0 2186.0 61.0 1489.0 0.0 1489.0 1218.0 4 100724.0 926.0 1123.0 82.0 1000.0 0.0 998.0 619.0 RET_PCF RRPTCT RRPTIN RRPTCTA RET_NMP RET_PCP STUFACR \ 0 54.0 6.0 0.0 6.0 2.0 33.0 18.0 1 86.0 42.0 0.0 42.0 20.0 48.0 20.0 2 50.0 NaN NaN NaN NaN NaN 13.0 3 82.0 8.0 0.0 8.0 2.0 25.0 19.0 4 62.0 19.0 0.0 19.0 1.0 5.0 15.0 Higher_Than_Avg_Ret_Rate Ret_Index 0 False -1.003257 1 True 1.359392 2 False -1.298588 3 True 1.064060 4 False -0.412595
In [108]:
pd.pivot_table(en2,
index = 'SECTOR LABEL',
values = ['RET_PCF', 'Ret_Index'],
aggfunc = np.mean).round(3)
Out[108]:
| RET_PCF | Ret_Index | |
|---|---|---|
| SECTOR LABEL | ||
| Private for-profit, 2-year | 70.000 | 0.178 |
| Private for-profit, 4-year or above | 65.196 | -0.177 |
| Private for-profit, less-than 2-year | 73.500 | 0.436 |
| Private not-for-profit, 2-year | 100.000 | 2.393 |
| Private not-for-profit, 4-year or above | 71.477 | 0.287 |
| Public, 2-year | 56.870 | -0.791 |
| Public, 4-year or above | 73.740 | 0.454 |
| Public, less-than 2-year | 81.000 | 0.990 |
In [109]:
pd.pivot_table(en2,
index = 'SECTOR LABEL',
values = ['RET_PCF', 'Ret_Index'],
aggfunc = np.mean).round(3)
Out[109]:
| RET_PCF | Ret_Index | |
|---|---|---|
| SECTOR LABEL | ||
| Private for-profit, 2-year | 70.000 | 0.178 |
| Private for-profit, 4-year or above | 65.196 | -0.177 |
| Private for-profit, less-than 2-year | 73.500 | 0.436 |
| Private not-for-profit, 2-year | 100.000 | 2.393 |
| Private not-for-profit, 4-year or above | 71.477 | 0.287 |
| Public, 2-year | 56.870 | -0.791 |
| Public, 4-year or above | 73.740 | 0.454 |
| Public, less-than 2-year | 81.000 | 0.990 |
In [110]:
piv_df = pd.pivot_table(en2,
index = 'SECTOR LABEL',
values = ['RET_PCF', 'Ret_Index'],
aggfunc = np.mean).round(3)
In [111]:
piv_df
Out[111]:
| RET_PCF | Ret_Index | |
|---|---|---|
| SECTOR LABEL | ||
| Private for-profit, 2-year | 70.000 | 0.178 |
| Private for-profit, 4-year or above | 65.196 | -0.177 |
| Private for-profit, less-than 2-year | 73.500 | 0.436 |
| Private not-for-profit, 2-year | 100.000 | 2.393 |
| Private not-for-profit, 4-year or above | 71.477 | 0.287 |
| Public, 2-year | 56.870 | -0.791 |
| Public, 4-year or above | 73.740 | 0.454 |
| Public, less-than 2-year | 81.000 | 0.990 |
In [112]:
piv_df.reset_index()
Out[112]:
| SECTOR LABEL | RET_PCF | Ret_Index | |
|---|---|---|---|
| 0 | Private for-profit, 2-year | 70.000 | 0.178 |
| 1 | Private for-profit, 4-year or above | 65.196 | -0.177 |
| 2 | Private for-profit, less-than 2-year | 73.500 | 0.436 |
| 3 | Private not-for-profit, 2-year | 100.000 | 2.393 |
| 4 | Private not-for-profit, 4-year or above | 71.477 | 0.287 |
| 5 | Public, 2-year | 56.870 | -0.791 |
| 6 | Public, 4-year or above | 73.740 | 0.454 |
| 7 | Public, less-than 2-year | 81.000 | 0.990 |
Saving to an Excel File¶
In [113]:
writer = pd.ExcelWriter('Retention Report.xlsx', engine = 'xlsxwriter')
piv_df.reset_index().to_excel(writer, sheet_name = 'Pivot_Table', index=False)
In [114]:
workbook = writer.book
worksheet = writer.sheets['Pivot_Table']
In [115]:
(max_row, max_col) = piv_df.shape
chart = workbook.add_chart({'type': 'column'})
chart.add_series({'values': ['Pivot_Table', 1, 1, max_row, 1]})
worksheet.insert_chart(1,3, chart)
format1 = workbook.add_format()
format1.set_align('left')
format2 = workbook.add_format({'num_format': '0.0%'})
format3 = workbook.add_format({'num_format': '0.0'})
worksheet.conditional_format('C2:C9', {'type': '3_color_scale'})
worksheet.set_column(0, 0, 35, format1)
worksheet.set_column(1, 1, 18, format3)
worksheet.set_column(2, 2, 18, format2)
writer.save()
Putting it all together¶
In [116]:
def get_the_data():
df = pd.read_html('https://nces.ed.gov/programs/digest/d21/tables/dt21_302.10.asp?current=yes')
df2 = df[3]
return df2
In [117]:
def clean_data(df2):
cols_to_keep = []
for c in df2.columns:
if '.1' not in c[4]:
cols_to_keep.append(c)
df3 = df2[cols_to_keep]
df3.columns = df3.columns.map(lambda x: x[3] + ' - ' + x[2])
df4 = df3[df3['Year - Year'] >= 2010]
df4['2-year college - Total'] = df4['2-year college - Total'].astype('float')
df4['4-year college or university - Total'] = df4['4-year college or university - Total'].astype('float')
df4['2-year college - Males'] = df4['2-year college - Males'].astype('float')
df4['4-year college or university - Males'] = df4['4-year college or university - Males'].astype('float')
df4['2-year college - Females'] = df4['2-year college - Females'].astype('float')
df4['4-year college or university - Females'] = df4['4-year college or university - Females'].astype('float')
return df4
In [118]:
def save_data(df4):
writer = pd.ExcelWriter('High School Data.xlsx', engine = 'xlsxwriter')
df4.to_excel(writer, sheet_name = 'Sheet1', index=False)
workbook = writer.book
worksheet = writer.sheets['Sheet1']
format1 = workbook.add_format({'num_format': '0'})
format2 = workbook.add_format({'num_format': '0.0'})
worksheet.conditional_format('E2:M12', {'type': '3_color_scale'})
worksheet.set_column(0, 0, 14)
worksheet.set_column(1, 1, 25, format1)
worksheet.set_column(2, 2, 25, format1)
worksheet.set_column(3, 3, 25, format1)
worksheet.set_column(4, 12, 18, format2)
writer.save()
In [119]:
df = get_the_data()
df2 = clean_data(df)
save_data(df2)
In [120]:
def get_the_data():
df = pd.read_html('https://nces.ed.gov/programs/digest/d21/tables/dt21_302.10.asp?current=yes')
df2 = df[3]
return df2
def clean_data(df2):
cols_to_keep = []
for c in df2.columns:
if '.1' not in c[4]:
cols_to_keep.append(c)
df3 = df2[cols_to_keep]
df3.columns = df3.columns.map(lambda x: x[3] + ' - ' + x[2])
df4 = df3[df3['Year - Year'] >= 2010]
df4['2-year college - Total'] = df4['2-year college - Total'].astype('float')
df4['4-year college or university - Total'] = df4['4-year college or university - Total'].astype('float')
df4['2-year college - Males'] = df4['2-year college - Males'].astype('float')
df4['4-year college or university - Males'] = df4['4-year college or university - Males'].astype('float')
df4['2-year college - Females'] = df4['2-year college - Females'].astype('float')
df4['4-year college or university - Females'] = df4['4-year college or university - Females'].astype('float')
return df4
def save_data(df4):
writer = pd.ExcelWriter('High School Data.xlsx', engine = 'xlsxwriter')
df4.to_excel(writer, sheet_name = 'Sheet1', index=False)
workbook = writer.book
worksheet = writer.sheets['Sheet1']
format1 = workbook.add_format({'num_format': '0'})
format2 = workbook.add_format({'num_format': '0.0'})
worksheet.conditional_format('E2:M12', {'type': '3_color_scale'})
worksheet.set_column(0, 0, 14)
worksheet.set_column(1, 1, 25, format1)
worksheet.set_column(2, 2, 25, format1)
worksheet.set_column(3, 3, 25, format1)
worksheet.set_column(4, 12, 18, format2)
writer.save()
df = get_the_data()
df2 = clean_data(df)
save_data(df2)
What's Next?¶
- Using Task Manager to Run Python Scripts on a Schedule 🔥
- Using Python and SQL together 💪
- Grabbing Data via APIs 📮
- Emailing Reports 🚀
Questions? 👏 😀 🔥 💗¶
